Neumann is an MCP server published by io.github.Kromatic-Innovation, hosted at neumann.kromatic.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 17 tools, including run_monte_carlo_simulation, rank_inputs_by_impact, summarize_outcome_scenarios, check_simulation_model, estimate_simulation_size_and_cost.
Monte Carlo ranges for uncertain plans: project cost, budget, timeline, capacity, NPV/IRR/payback.
5 connections through 4 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Runs a Monte Carlo simulation of a model and returns the full range of possible outcomes, not one guessed number. A model is a set of uncertain inputs, the formulas that combine them, and the links between them. The simulation draws random values for every input many times; each draw is a trial, and one call is one run. Use this when you need to know how likely different outcomes are for a plan built on uncertain inputs: a project's total cost or budget (for example from low / most likely / high estimates per line item), a schedule or delivery date, capacity, revenue, or an investment's NPV, IRR or payback. It returns a summary: for each output node (the nodes nothing else depends on, or the ones you list in run_params.output_request.nodes) the mean, the 10th, 50th and 90th percentiles (the value that share of trials fall below), the minimum and maximum in the last time period, and the same per period; plus any metrics you asked for, such as NPV, IRR, payback or the chance of beating a target or budget; and a run_id. Pass that run_id to get_simulation_results for other nodes, periods or percentiles. A run that takes longer than about 40 seconds keeps running in the background: you get status running and a run_id, and get_simulation_results gives you progress and then the result. Cost: without an account, 1 of your 3 free runs per UTC day, for a model up to 1,000 trials and 20 nodes; that daily allowance is counted per network address and client, so on a shared platform such as Claude.ai or ChatGPT you may find today's free runs already spent by someone else. Signed in with a free Kromatic account, 1 of 10 free runs per UTC day, for a small model (trials x nodes x periods at most 100,000, and within 10,000 trials and 50 nodes), spent before any credits. Beyond that -- a larger model, or a day whose free runs are used up -- 1 credit for a small run or 5 for a large one, currently $0.50 per credit; buy_credits tops up. A model that is invalid, or over the limits of the tier you are in, is rejected before running and costs nothing. If it fails mid-run, it depends on the tier: without an account the free run is still used up and not given back; signed in on a free run, the free run is given back; on credits, you are not charged.
Schema too large to show here (25,280 characters).
{
"name": "run_monte_carlo_simulation",
"title": "Run a Monte Carlo simulation of a model",
"description": "Runs a Monte Carlo simulation of a model and returns the full range of possible outcomes, not one guessed number. A model is a set of uncertain inputs, the formulas that combine them, and the links between them. The simulation draws random values for every input many times; each draw is a trial, and one call is one run. Use this when you need to know how likely different outcomes are for a plan built on uncertain inputs: a project's total cost or budget (for example from low / most likely / high estimates per line item), a schedule or delivery date, capacity, revenue, or an investment's NPV, IRR or payback. It returns a summary: for each output node (the nodes nothing else depends on, or the ones you list in run_params.output_request.nodes) the mean, the 10th, 50th and 90th percentiles (the value that share of trials fall below), the minimum and maximum in the last time period, and the same per period; plus any metrics you asked for, such as NPV, IRR, payback or the chance of beating a target or budget; and a run_id. Pass that run_id to get_simulation_results for other nodes, periods or percentiles. A run that takes longer than about 40 seconds keeps running in the background: you get status running and a run_id, and get_simulation_results gives you progress and then the result. Cost: without an account, 1 of your 3 free runs per UTC day, for a model up to 1,000 trials and 20 nodes; that daily allowance is counted per network address and client, so on a shared platform such as Claude.ai or ChatGPT you may find today's free runs already spent by someone else. Signed in with a free Kromatic account, 1 of 10 free runs per UTC day, for a small model (trials x nodes x periods at most 100,000, and within 10,000 trials and 50 nodes), spent before any credits. Beyond that -- a larger model, or a day whose free runs are used up -- 1 credit for a small run or 5 for a large one, currently $0.50 per credit; buy_credits tops up. A model that is invalid, or over the limits of the tier you are in, is rejected before running and costs nothing. If it fails mid-run, it depends on the tier: without an account the free run is still used up and not given back; signed in on a free run, the free run is given back; on credits, you are not charged.",
"inputSchema": {
"truncated": true,
"chars": 25280
},
"outputSchema": {
"type": "object",
"$defs": {
"Histogram": {
"type": "object",
"title": "Histogram",
"required": [
"counts",
"bins"
],
"properties": {
"bins": {
"type": "array",
"items": {
"type": "number"
},
"title": "Bins"
},
"counts": {
"type": "array",
"items": {
"type": "integer"
},
"title": "Counts"
}
},
"description": "Histogram of trial values: counts per bin, and the bin edges (one more edge than counts)."
},
"BasicStats": {
"type": "object",
"title": "BasicStats",
"required": [
"mean",
"std",
"min",
"max"
],
"properties": {
"max": {
"type": "number",
"title": "Max"
},
"min": {
"type": "number",
"title": "Min"
},
"std": {
"type": "number",
"title": "Std"
},
"mean": {
"type": "number",
"title": "Mean"
}
},
"description": "Mean, standard deviation, minimum and maximum across trials."
},
"RunSummary": {
"type": "object",
"title": "RunSummary",
"required": [
"trials",
"time_periods"
],
"properties": {
"note": {
"type": "string",
"title": "Note",
"default": "This is a summary. For other nodes, periods, percentiles, the chance of reaching a threshold, or a histogram, call get_simulation_results with this run_id and the nodes, periods, percentiles, threshold or histogram arguments."
},
"trials": {
"type": "integer",
"title": "Trials"
},
"metrics": {
"type": "array",
"items": {
"$ref": "#/$defs/MetricSummary"
},
"title": "Metrics"
},
"outputs": {
"type": "array",
"items": {
"$ref": "#/$defs/OutputNodeSummary"
},
"title": "Outputs"
},
"other_nodes": {
"type": "array",
"items": {
"type": "string"
},
"title": "Other Nodes",
"description": "Ids of the other nodes, which you can query by name."
},
"time_periods": {
"type": "integer",
"title": "Time Periods"
},
"other_nodes_count": {
"type": "integer",
"title": "Other Nodes Count",
"default": 0,
"description": "How many other nodes there are."
}
},
"description": "Headline numbers: output nodes, requested metrics, and the ids of the other nodes you can ask get_simulation_results about."
},
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"Percentiles": {
"type": "object",
"title": "Percentiles",
"required": [
"p10",
"p25",
"p50",
"p75",
"p90"
],
"properties": {
"p10": {
"type": "number",
"title": "P10"
},
"p25": {
"type": "number",
"title": "P25"
},
"p50": {
"type": "number",
"title": "P50"
},
"p75": {
"type": "number",
"title": "P75"
},
"p90": {
"type": "number",
"title": "P90"
}
},
"description": "10th, 25th, 50th (median), 75th and 90th percentiles across trials, estimated from a histogram."
},
"RunProgress": {
"type": "object",
"title": "RunProgress",
"required": [
"percent",
"done",
"total",
"unit"
],
"properties": {
"done": {
"type": "integer",
"title": "Done"
},
"unit": {
"enum": [
"trials",
"runs"
],
"type": "string",
"title": "Unit",
"description": "trials for a simulation; runs (internal simulations) for a sensitivity sweep."
},
"total": {
"type": "integer",
"title": "Total"
},
"percent": {
"type": "number",
"title": "Percent",
"description": "0 to 100."
}
},
"description": "How far a queued or running run has got."
},
"OutputSeries": {
"type": "object",
"title": "OutputSeries",
"required": [
"periods",
"mean",
"p10",
"p50",
"p90"
],
"properties": {
"p10": {
"type": "array",
"items": {
"type": "number"
},
"title": "P10"
},
"p50": {
"type": "array",
"items": {
"type": "number"
},
"title": "P50"
},
"p90": {
"type": "array",
"items": {
"type": "number"
},
"title": "P90"
},
"mean": {
"type": "array",
"items": {
"type": "number"
},
"title": "Mean"
},
"periods": {
"type": "array",
"items": {
"type": "integer"
},
"title": "Periods",
"description": "Period indices, counted from 0."
}
},
"description": "An output node over time, sampled to at most 24 periods."
},
"MetricSummary": {
"type": "object",
"title": "MetricSummary",
"required": [
"id",
"mean",
"p10",
"p50",
"p90"
],
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"p10": {
"type": "number",
"title": "P10"
},
"p50": {
"type": "number",
"title": "P50"
},
"p90": {
"type": "number",
"title": "P90"
},
"mean": {
"type": "number",
"title": "Mean"
},
"target": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Target",
"default": null,
"description": "The node or metric it was computed on."
},
"function": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Function",
"default": null
},
"probability": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Probability",
"default": null,
"description": "For a prob metric: the probability (0 to 1), which is its mean."
}
},
"description": "One requested metric across trials. For a prob metric, probability is the chance (0 to 1)."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"SummaryElement": {
"type": "object",
"title": "SummaryElement",
"required": [
"percentiles",
"basic_stats"
],
"properties": {
"raw": {
"anyOf": [
{
"type": "array",
"items": {
"type": "number"
}
},
{
"type": "null"
}
],
"title": "Raw",
"default": null,
"description": "Per-trial values. Not returned by this tool (always null)."
},
"histogram": {
"anyOf": [
{
"$ref": "#/$defs/Histogram"
},
{
"type": "null"
}
],
"default": null
},
"basic_stats": {
"$ref": "#/$defs/BasicStats"
},
"percentiles": {
"$ref": "#/$defs/Percentiles"
}
},
"description": "Statistics for one node or edge in one period."
},
"TruncationInfo": {
"type": "object",
"title": "TruncationInfo",
"required": [
"applied",
"hint"
],
"properties": {
"hint": {
"type": "string",
"title": "Hint",
"description": "How to get the omitted data."
},
"applied": {
"type": "array",
"items": {
"type": "string"
},
"title": "Applied",
"description": "The reductions applied, in order."
}
},
"description": "What the default summary left out of the result."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
},
"SimulationResult": {
"type": "object",
"title": "SimulationResult",
"required": [
"trials",
"time_periods"
],
"properties": {
"trials": {
"type": "integer",
"title": "Trials"
},
"aggregations": {
"type": "object",
"title": "Aggregations",
"description": "Requested financial metrics, keyed by their id. Each is the distribution of that metric across trials. For a prob metric, the mean is the probability. Trials where a metric is undefined (for example IRR that never converges) are left out.",
"additionalProperties": {
"$ref": "#/$defs/SummaryElement"
}
},
"time_periods": {
"type": "integer",
"title": "Time Periods"
},
"contract_version": {
"type": "string",
"const": "1.0",
"title": "Contract Version",
"default": "1.0"
},
"summary_statistics": {
"type": "array",
"items": {
"$ref": "#/$defs/SummaryTimePeriod"
},
"title": "Summary Statistics"
}
},
"description": "Summarized outcomes. summary_statistics has one entry per time period; aggregations holds the financial metrics you requested."
},
"OutputNodeSummary": {
"type": "object",
"title": "OutputNodeSummary",
"required": [
"node_id",
"period",
"mean",
"p10",
"p50",
"p90",
"min",
"max"
],
"properties": {
"max": {
"type": "number",
"title": "Max"
},
"min": {
"type": "number",
"title": "Min"
},
"p10": {
"type": "number",
"title": "P10"
},
"p50": {
"type": "number",
"title": "P50"
},
"p90": {
"type": "number",
"title": "P90"
},
"mean": {
"type": "number",
"title": "Mean"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name",
"default": null
},
"period": {
"type": "integer",
"title": "Period",
"description": "The period these numbers describe (the last one)."
},
"series": {
"anyOf": [
{
"$ref": "#/$defs/OutputSeries"
},
{
"type": "null"
}
],
"default": null,
"description": "Mean and P10/P50/P90 per period. Absent for a one-period model."
},
"node_id": {
"type": "string",
"title": "Node Id"
}
},
"description": "One output node: mean, 10th/50th/90th percentiles, minimum and maximum in the last period, and a per-period series."
},
"SummaryTimePeriod": {
"type": "object",
"title": "SummaryTimePeriod",
"required": [
"time_period"
],
"properties": {
"edges": {
"type": "object",
"title": "Edges",
"additionalProperties": {
"$ref": "#/$defs/SummaryElement"
}
},
"nodes": {
"type": "object",
"title": "Nodes",
"additionalProperties": {
"$ref": "#/$defs/SummaryElement"
}
},
"time_period": {
"type": "integer",
"title": "Time Period"
}
},
"description": "Every node and edge for one time period (index counted from 0)."
}
},
"title": "RunMonteCarloSimulationResult",
"required": [
"run_id",
"status",
"tier",
"total_trials"
],
"properties": {
"tier": {
"type": "string",
"title": "Tier",
"description": "small or large; sets the credit price for an account."
},
"result": {
"anyOf": [
{
"$ref": "#/$defs/SimulationResult"
},
{
"type": "null"
}
],
"default": null,
"description": "Every node and edge per period (only with detail full)."
},
"run_id": {
"type": "string",
"title": "Run Id",
"description": "Id of this run. Pass it to get_simulation_results for progress, the result, or specific numbers."
},
"status": {
"enum": [
"completed",
"running",
"queued"
],
"type": "string",
"title": "Status",
"description": "completed, or running / queued: the run continues in the background, so call get_simulation_results with run_id. A run that fails within this call returns an error instead."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost."
},
"summary": {
"anyOf": [
{
"$ref": "#/$defs/RunSummary"
},
{
"type": "null"
}
],
"default": null,
"description": "The headline numbers (the default)."
},
"progress": {
"anyOf": [
{
"$ref": "#/$defs/RunProgress"
},
{
"type": "null"
}
],
"default": null,
"description": "Percent done while the run is running or queued."
},
"next_step": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Next Step",
"default": null,
"description": "What to do while the run is still going."
},
"truncation": {
"anyOf": [
{
"$ref": "#/$defs/TruncationInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Present only when the summary left data out to stay small: what was left out and how to get it."
},
"total_trials": {
"type": "integer",
"title": "Total Trials",
"description": "Number of trials run."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits charged (0 without an account)."
},
"estimated_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Estimated Seconds",
"default": null,
"description": "Rough total run time, in seconds."
}
},
"description": "Result of one run: a summary when it finished within the call, or status running and a run_id when it is still going."
},
"annotations": {
"title": "Run a Monte Carlo simulation of a model",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Ranks a model's uncertain inputs by how much each one moves a chosen outcome, and returns the data for a tornado chart (a bar chart with one horizontal bar per input, the biggest swing at the top). This is a one-at-a-time (OAT) sensitivity analysis: it shows how much the outcome changes when each input changes on its own. Every input is held at its median while one input at a time is set to low, middle and high values from its own distribution (by default its 5th, 50th and 95th percentiles). The tool records how the outcome's average changes. Use this when you need to know which assumption matters most, so you know what to research or de-risk first. It returns one entry per input, ranked so rank 1 has the biggest impact. Each entry lists the input values tried, the outcome at each, and an elasticity score. Elasticity is about how many percent the outcome's average moves when the input moves 1 percent, averaged over the values tried. It is never negative: it says how much an input matters, not which way it pushes the outcome; to see the direction, compare the outcome at the input's low and high values. It returns numbers, not an image. Inputs whose distribution produces a list of values are skipped. It always returns a run_id. It runs the model once per input per value tried, so on a big model it can take minutes: if it is not done in about 40 seconds you get status running, and get_simulation_results gives you progress and then the ranking. Cost: it counts as one run per call, however many times it runs the model inside, and it is charged only if the analysis succeeds. Without an account, 1 of your 3 free runs per UTC day, for a model up to 1,000 trials and 20 nodes; that daily allowance is counted per network address and client, so on a shared platform such as Claude.ai or ChatGPT you may find today's free runs already spent by someone else. Signed in with a free Kromatic account, 1 of 10 free runs per UTC day, for a small model (trials x nodes x periods at most 100,000, and within 10,000 trials and 50 nodes), spent before any credits. Beyond that, 1 credit for a small model or 5 for a large one, currently $0.50 per credit; buy_credits tops up. A model that is invalid, or over the limits of the tier you are in, is rejected before running and costs nothing, and so is a saved graph refused with incomplete_model: no credit, no free run, no run recorded. If the analysis fails partway through, it depends on what paid for it: without an account the free run is used up and not given back; a signed-in free run is given back; credits are not charged.
| Parameter | Type |
|---|
Reports one outcome's worst, median and best cases from one run of a model. By default, worst is the lowest value in any trial, median is the middle value, and best is the highest value. Those labels assume higher is better. For a cost or a duration, where lower is better, swap them when you tell the user: the scenario labelled worst is the cheapest or fastest case, which is the good outcome, and the one labelled best is the most expensive or slowest. You can ask for other percentiles instead, such as the 10th and 90th, or the 80th for a P80 total. Use this when you want a short worst, typical and best case story. For the range or the odds of outcomes (what range it could land in, how likely something is), use run_monte_carlo_simulation instead; to find which input matters most, use rank_inputs_by_impact. It takes the model inline in graph, or a saved model by graph_id directly, so you do not need get_graph first. If an input in the saved graph has no distribution yet, the call is refused with incomplete_model and costs nothing. It returns each scenario's outcome value and every input's own value at the same percentile of that input's distribution. Those input values are an estimate, not the exact inputs of that trial. It also returns a run_id; a long run comes back as status running, and get_simulation_results gives you progress and then the result. Cost: without an account, 1 of your 3 free runs per UTC day, for a model up to 1,000 trials and 20 nodes; that daily allowance is counted per network address and client, so on a shared platform such as Claude.ai or ChatGPT you may find today's free runs already spent by someone else. Signed in with a free Kromatic account, 1 of 10 free runs per UTC day, for a small model (trials x nodes x periods at most 100,000, and within 10,000 trials and 50 nodes), spent before any credits. Beyond that -- a larger model, or a day whose free runs are used up -- 1 credit for a small run or 5 for a large one, currently $0.50 per credit; buy_credits tops up. A model that is invalid, or over the limits of the tier you are in, is rejected before running and costs nothing. If it fails mid-run, it depends on the tier: without an account the free run is still used up and not given back; signed in on a free run, the free run is given back; on credits, you are not charged.
| Parameter | Type | Description |
|---|---|---|
| seed | any | Optional whole number that fixes the random draws, so repeating the call gives the same result. Exact repeats are guaranteed only for small runs, where trials × nodes × time periods is at most 100,000. |
Checks a model you hold inline for mistakes, before you save or run it, and lists every problem it finds. It looks for loops with no delay, nodes that are not connected, unknown distributions, missing or invalid distribution parameters, and broken formulas. A loop, including an edge from a node to itself, is allowed and is not an error when at least one edge in it has delay 1 or more. Use this when you have built or edited a model and want to fix it without spending a run. It takes the model inline, not a graph_id: to check a saved model, read it with get_graph and pass what that returns. It does not run or rank anything, and it does not say what a run will cost (use estimate_simulation_size_and_cost for that). It returns is_valid and a list of issues. A draft input with no distribution yet (distribution_type null) is not rejected: it comes back as an issue with severity error naming that input, and is_valid is false, so the model is not ready to run until each such input has a distribution. You do not need this tool to learn that an input with only a low-high guess cannot run: it cannot, and convert_range_to_distribution turns the guess into a distribution. Each issue gives the rule broken, a severity (error, warning or info, where info is only a note), a message, and the node and edge ids involved. If an edge points at a node that does not exist, or the model is over your tier's size limit, you get an error message instead of the list. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs. Without an account, a model over 1,000 trials or 20 nodes is rejected, also at no cost.
| Parameter | Type | Description |
|---|---|---|
| graph * | object | The model: root_nodes (uncertain inputs), calc_nodes (formulas), edges (links; formulas refer to them like {e1}) and run_params (trials and time periods). Same format as run_monte_carlo_simulation's graph, which documents formulas, periods, distributions and financial metrics in full. Unlike there, … |
Predicts how large a run of a model will be and how many credits it will cost, without running it. Use this before running a large or unfamiliar model, or to check that an account can afford it. It does not look for mistakes; use check_simulation_model for that. It returns the number of trials, time periods, nodes and edges, the estimated peak memory in MB, a complexity score, the size tier (small or large), the credit cost for an account, and a rough run time in seconds for run_monte_carlo_simulation and for rank_inputs_by_impact (which runs the model many times). Runs over about 40 seconds continue in the background and are collected with get_simulation_results. A run is small when trials × nodes × time periods is at most 100,000, and large otherwise. Accounts have no fixed trial or node limit. That cost is what run_monte_carlo_simulation, summarize_outcome_scenarios and rank_inputs_by_impact each charge for this model. A model with mistakes returns an error instead of an estimate. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs. Without an account, a model over 1,000 trials or 20 nodes is rejected, also at no cost.
| Parameter | Type | Description |
|---|---|---|
| graph * | object | The model: root_nodes (uncertain inputs), calc_nodes (formulas), edges (links; formulas refer to them like {e1}) and run_params (trials and time periods). Same format as run_monte_carlo_simulation's graph, which documents formulas, periods, distributions and financial metrics in full. Only this outl… |
{
"name": "estimate_simulation_size_and_cost",
"title": "Estimate a simulation's cost and size before running it",
"description": "Predicts how large a run of a model will be and how many credits it will cost, without running it. Use this before running a large or unfamiliar model, or to check that an account can afford it. It does not look for mistakes; use check_simulation_model for that. It returns the number of trials, time periods, nodes and edges, the estimated peak memory in MB, a complexity score, the size tier (small or large), the credit cost for an account, and a rough run time in seconds for run_monte_carlo_simulation and for rank_inputs_by_impact (which runs the model many times). Runs over about 40 seconds continue in the background and are collected with get_simulation_results. A run is small when trials × nodes × time periods is at most 100,000, and large otherwise. Accounts have no fixed trial or node limit. That cost is what run_monte_carlo_simulation, summarize_outcome_scenarios and rank_inputs_by_impact each charge for this model. A model with mistakes returns an error instead of an estimate. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs. Without an account, a model over 1,000 trials or 20 nodes is rejected, also at no cost.",
"inputSchema": {
"type": "object",
"title": "EstimateSimulationSizeAndCostInput",
"required": [
"graph"
],
"properties": {
"graph": {
"type": "object",
"examples": [
{
"edges": [
{
"id": "e1",
"source": "customers",
"target": "revenue"
},
{
"id": "e2",
"source": "price",
"target": "revenue"
}
],
"calc_nodes": [
{
"id": "revenue",
"name": "Monthly revenue",
"formula": "{e1} * {e2}"
}
],
"root_nodes": [
{
"id": "customers",
"name": "Customers per month",
"distribution_type": "normal",
"distribution_params": {
"std": 200,
"mean": 1000
}
},
{
"id": "price",
"name": "Price (USD)",
"distribution_type": "triangle",
"distribution_params": {
"max_val": 15,
"min_val": 8,
"mode_val": 10
}
}
],
"run_params": {
"trials": 1000,
"time_periods": 12
}
}
],
"description": "The model: root_nodes (uncertain inputs), calc_nodes (formulas), edges (links; formulas refer to them like {e1}) and run_params (trials and time periods). Same format as run_monte_carlo_simulation's graph, which documents formulas, periods, distributions and financial metrics in full. Only this outline is published here: the full schema is on run_monte_carlo_simulation's graph parameter, and the neumann://catalog resource lists every distribution and formula function. Neumann checks the model against that full schema when you call this tool and names any problem."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "EstimateSimulationSizeAndCostResult",
"required": [
"trials",
"time_periods",
"node_count",
"edge_count",
"estimated_memory_mb",
"graph_complexity",
"tier",
"credit_cost"
],
"properties": {
"tier": {
"type": "string",
"title": "Tier",
"description": "small when trials × nodes × time periods is at most 100,000, otherwise large."
},
"trials": {
"type": "integer",
"title": "Trials"
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"edge_count": {
"type": "integer",
"title": "Edge Count"
},
"node_count": {
"type": "integer",
"title": "Node Count"
},
"credit_cost": {
"type": "integer",
"title": "Credit Cost",
"description": "Credits an account would be charged by run_monte_carlo_simulation, summarize_outcome_scenarios or rank_inputs_by_impact for this model."
},
"time_periods": {
"type": "integer",
"title": "Time Periods"
},
"graph_complexity": {
"type": "integer",
"title": "Graph Complexity",
"description": "A relative complexity score; higher means heavier."
},
"estimated_seconds": {
"type": "number",
"title": "Estimated Seconds",
"default": 0,
"description": "Rough run time of one run_monte_carlo_simulation or summarize_outcome_scenarios call, in seconds."
},
"estimated_memory_mb": {
"type": "number",
"title": "Estimated Memory Mb",
"description": "Estimated peak memory, in MB."
},
"estimated_seconds_rank_inputs": {
"type": "number",
"title": "Estimated Seconds Rank Inputs",
"default": 0,
"description": "Rough run time of rank_inputs_by_impact with its default three values per input, in seconds. Over about 40 seconds, it finishes in the background."
}
},
"description": "Predicted size and credit cost of a run, without running it."
},
"annotations": {
"title": "Estimate a simulation's cost and size before running it",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Turns a low-to-high guess, such as "between 80 and 120, 90% sure", into the exact parameters a model input needs. A distribution is the shape of the uncertainty, for example normal (a bell curve), log_normal (skewed and never negative), triangle or uniform. The low and high values are the edges of the range you are that sure of, not hard limits. Use this when you have a rough estimate and need distribution parameters instead of guessing them: an input with only a low-high guess has no distribution yet and cannot run until it has one. You do not need it for a three-point low / most likely / high estimate: that goes straight into the model as a triangle input (min_val, mode_val, max_val), so call run_monte_carlo_simulation directly. Its reverse is convert_distribution_to_range. It returns the distribution type and its parameters, ready to use as a model input's distribution_params. The distribution_type parameter explains which type fits which kind of quantity. Supported types: normal, log_normal, uniform, triangle, beta, gamma, exponential, binomial, discrete_normal, discrete_lognormal, discrete_gamma, constant and bernoulli. Not supported: poisson, categorical, dirichlet, multivariate_normal and constant_array. For beta, give low and high as fractions (2% is 0.02). Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.
| Parameter | Type | Description |
|---|---|---|
| max_estimate | any | The high end of your range. Required for every type except constant and bernoulli. |
| min_estimate | any | The low end of your range. Required for every type except constant and bernoulli. Exponential ignores it, but a value must still be sent (any number works). |
| mode_estimate | any | The most likely value. Required for constant (the fixed value), bernoulli (the chance of success, from 0 to 1) and binomial. For triangle it sets the peak; it must lie strictly between low and high, and defaults to their midpoint. For beta it is used as the peak when a fit allows, but the low and hi… |
Turns a distribution's parameters into the low and high ends of the range that holds a chosen share of outcomes, by default the middle 90%. It also gives the mean, median, mode, standard deviation and any percentiles you ask for. If you give a threshold, it gives the chance of landing below and above it. Use this when you have distribution parameters, from a model or from fermi (a companion forecasting server from Kromatic, the company behind Neumann, whose estimates carry next_steps.simulate.root_node), and want to know what they mean in plain numbers. Its reverse is convert_range_to_distribution, and the range it returns can be passed straight back to it. Values that do not apply, such as a uniform distribution's mode, come back as null with a note explaining why. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.
| Parameter | Type | Description |
|---|---|---|
| quantiles | any | A list of percentiles to report. Each is a fraction from 0 to 1: 0.05 is the 5th percentile, the value 5% of outcomes fall below. No repeats. Default [0.05, 0.1, 0.5, 0.9, 0.95], returned under keys p5, p10, p50, p90 and p95. |
| threshold | any | Optional value to compare against. The result gives the chance of being at or below it and the chance of being above it. For whole-number distributions it gives the chance of being below and above it, and notes the chance of landing exactly on it. |
| percentile_range | number | A single fraction: the share of outcomes the returned range should hold, centred on the median. The default 0.9 means the middle 90%, so the range runs from the 5th to the 95th percentile. |
| distribution_type * | string | The distribution's name. Accepts every type a model input accepts: normal, log_normal, uniform, triangle, beta (values are fractions from 0 to 1), gamma, exponential, poisson, bernoulli, binomial, categorical, constant, discrete_normal, discrete_lognormal and discrete_gamma. categorical returns no r… |
Checks on, and reads, a run you started with run_monte_carlo_simulation, rank_inputs_by_impact or summarize_outcome_scenarios, using its run_id. Use this when a run tool returned status running or queued: it waits up to 30 seconds for the run to finish, then returns its status and percent done, or the finished result, so call it again until status is completed. Use it also to get specific numbers from a finished simulation without running it again (a finished run keeps every node's and edge's statistics for every period): pass nodes (node, edge or metric ids), periods, percentiles such as 0.05 or 0.95, a threshold to get the chance a value is at least or at most some number, or histogram for the distribution's shape. Without those it returns the summary (or the ranking, or the scenarios). A failed run returns its error and is not charged. Only the caller who started the run can read it, and only with the run_id, which is returned to that caller alone. A run started without an account can be read for 24 hours and only from the same network address and client, because a caller without an account is recognized by them; sign in with a free Kromatic account for runs that are not tied to one connection. Credentials go in the Authorization header as a Bearer credential; no Neumann tool takes an api_key argument. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.
| Parameter | Type | Description |
|---|---|---|
| nodes | any | Ids of the nodes, edges or metrics (output_request.aggregations ids) to return numbers for. Default: the output nodes. |
| run_id * | string | The run_id returned by run_monte_carlo_simulation, rank_inputs_by_impact or summarize_outcome_scenarios. |
| periods | any | Time period indices to return, counting from 0. Default: the last period only. Ignored for metrics, which cover the whole run. |
| histogram |
Shows who Neumann thinks you are and what you can still do: your free runs left today and when they reset, and your credit balance if you have an account. Use this when you need to know, before or after a run, whether the next call will be free or spend credits, how much is left, or whether you are signed in -- and when a run was refused for want of runs or credits, so you can tell the user which it was. There are three tiers. Without an account you get 3 free runs per UTC day; you are recognized by network address and client, so on a hosted platform such as Claude.ai or ChatGPT many callers share one identity and today's free runs may already be spent by someone else. Signed in with a free Kromatic account you get your own 10 free runs per UTC day, spent before any credits. After those, runs cost credits. An account created with POST https://neumann.kromatic.com/api/v1/accounts authenticates you and starts with 5 free credits, but it carries no free daily runs -- only signing in with a Kromatic account does. It returns whether you are anonymous or an account, your account id and status, credit balance, free runs left today with the reset time and the size limits that apply to you, the price of one credit in US dollars, and your last 10 credit transactions. With an account it also returns how many models are saved on your account and the three most recently updated, each with its graph_id, so when the user mentions a saved model you can often go straight to get_graph without calling list_graphs. Credentials go in the Authorization header as a Bearer credential and nowhere else; no Neumann tool takes an api_key argument, and a credential that is not recognized returns an unauthorized error. This tool itself needs no account -- it is how a caller without one finds that out. Setup docs: https://kromatic.com/mcp/neumann. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.
No parameters.
{
"name": "check_account_and_credits",
"title": "Check your account, credits and free runs left",
"description": "Shows who Neumann thinks you are and what you can still do: your free runs left today and when they reset, and your credit balance if you have an account. Use this when you need to know, before or after a run, whether the next call will be free or spend credits, how much is left, or whether you are signed in -- and when a run was refused for want of runs or credits, so you can tell the user which it was. There are three tiers. Without an account you get 3 free runs per UTC day; you are recognized by network address and client, so on a hosted platform such as Claude.ai or ChatGPT many callers share one identity and today's free runs may already be spent by someone else. Signed in with a free Kromatic account you get your own 10 free runs per UTC day, spent before any credits. After those, runs cost credits. An account created with POST https://neumann.kromatic.com/api/v1/accounts authenticates you and starts with 5 free credits, but it carries no free daily runs -- only signing in with a Kromatic account does. It returns whether you are anonymous or an account, your account id and status, credit balance, free runs left today with the reset time and the size limits that apply to you, the price of one credit in US dollars, and your last 10 credit transactions. With an account it also returns how many models are saved on your account and the three most recently updated, each with its graph_id, so when the user mentions a saved model you can often go straight to get_graph without calling list_graphs. Credentials go in the Authorization header as a Bearer credential and nowhere else; no Neumann tool takes an api_key argument, and a credential that is not recognized returns an unauthorized error. This tool itself needs no account -- it is how a caller without one finds that out. Setup docs: https://kromatic.com/mcp/neumann. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.",
"inputSchema": {
"type": "object",
"title": "CheckAccountAndCreditsInput",
"properties": {}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"LedgerEntry": {
"type": "object",
"title": "LedgerEntry",
"required": [
"entry_type",
"amount",
"created_at"
],
"properties": {
"amount": {
"type": "integer",
"title": "Amount",
"description": "Credits added (positive) or used (negative)."
},
"created_at": {
"type": "string",
"title": "Created At",
"description": "When it happened, as an ISO-8601 time."
},
"entry_type": {
"type": "string",
"title": "Entry Type",
"description": "Kind of transaction, for example signup_grant or run_debit."
},
"request_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Request Id",
"default": null,
"description": "Internal reference for the transaction."
}
},
"description": "One credit transaction."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
},
"SavedGraphEntry": {
"type": "object",
"title": "SavedGraphEntry",
"required": [
"graph_id",
"name",
"updated_at"
],
"properties": {
"name": {
"type": "string",
"title": "Name",
"description": "The name the model is saved under."
},
"graph_id": {
"type": "string",
"title": "Graph Id",
"description": "The model's id. Pass it to get_graph, rank_inputs_by_impact, summarize_outcome_scenarios or delete_graph."
},
"updated_at": {
"type": "string",
"title": "Updated At",
"description": "When the model was last saved, as an ISO-8601 time."
}
},
"description": "One saved model."
},
"SavedGraphsSummary": {
"type": "object",
"title": "SavedGraphsSummary",
"required": [
"count",
"newest"
],
"properties": {
"count": {
"type": "integer",
"title": "Count",
"description": "How many models are saved on your account: the number list_graphs lists in total."
},
"newest": {
"type": "array",
"items": {
"$ref": "#/$defs/SavedGraphEntry"
},
"title": "Newest",
"description": "Up to 3 saved models, most recently updated first. Pass a graph_id to get_graph; for any other saved model, call list_graphs."
}
},
"description": "The models saved on your account."
}
},
"title": "CheckAccountAndCreditsResult",
"required": [
"price_per_credit_usd"
],
"properties": {
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"saved_graphs": {
"anyOf": [
{
"$ref": "#/$defs/SavedGraphsSummary"
},
{
"type": "null"
}
],
"default": null,
"description": "How many models are saved on your account and the three most recently updated. Null without an account."
},
"recent_ledger": {
"anyOf": [
{
"type": "array",
"items": {
"$ref": "#/$defs/LedgerEntry"
}
},
{
"type": "null"
}
],
"title": "Recent Ledger",
"default": null,
"description": "Your last 10 credit transactions, newest first. Null without an account."
},
"price_per_credit_usd": {
"type": "number",
"title": "Price Per Credit Usd",
"description": "Current price of one credit in US dollars."
}
},
"description": "Your identity, balance or free runs left (in billing), the credit price, recent credit history, and a summary of your saved models."
},
"annotations": {
"title": "Check your account, credits and free runs left",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Sends a short report about Neumann to the team that builds it. Use this when the user wants to report a problem, a wrong result, a confusing message or a missing feature (including asking you to pass a request or suggestion on to the team), or has agreed to your offer to send one. Send only after the user agrees: when a tool fails, first tell the user what happened and ask, and do not call this tool until they say yes. Good moments to offer: a tool returned an error or a result that looks wrong, the user needed something Neumann could not do, or the work with Neumann is wrapping up and the user might want to say what worked. Offer it as a question, for example: 'Want me to send Neumann's team a short note about this?' The team reads every report. Do not offer after each routine successful call. Put several points in one report: a signed-in account may send 5 per hour and 20 per day, and callers without an account share 60 per hour and 300 per day. Only message is required. Fill in the other fields that apply so the team can act without guessing. Write in your own words. Never include personal data (names, email addresses, company names), the user's own numbers (inputs or results), secrets or keys, or the conversation transcript; describe the task and any wrong result in general terms instead. Add sender_email only if the user wants a reply. If you are signed in, your account id is included. No account is needed. It returns status "sent". Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.
| Parameter | Type | Description |
|---|---|---|
| impact | any | How much it cost the user. blocked: could not finish. workaround: finished another way. minor: an annoyance. none: no cost, for example praise. |
| run_id | any | The run_id the report is about, if a run was involved. |
| message * | string | The report, in your own words, 10 to 5,000 characters. Say what you tried, what happened and what you expected. Leave out names, companies, the user's numbers (inputs or results) and the conversation itself: write "a revenue forecast", not its figures. |
Charges the payment card saved on the user's account to buy Neumann credits; without a saved card it charges nothing and returns a checkout link instead. One call buys at most 100 credits ($50.00 at today's price); a request for more is refused and charges nothing. When the user asks for more than that, do not call it yet: tell them the limit and ask how many to buy now. A second purchase needs the user's agreement again. Credits pay for runs once the free runs for the day are used up, or for a model too large to run free. Use this when an account is low on credits and the user has agreed to the purchase; to see the balance and the live price first, call check_account_and_credits. When no card is saved yet, it returns payment_status checkout_required and a checkout_url, which the user opens in a browser to save a card before you call this tool again. It returns the credits bought, the new balance, the payment status and, when a card is needed, the checkout_url. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. When you are signed in rather than using a key, the sign-in must include billing access (the neumann:billing scope); without it the call is refused with insufficient_scope and charges nothing, and the user signs in again to grant it. Cost: charges the payment card saved on your account for each credit, currently $0.50 per credit (check_account_and_credits shows the live price). It needs an account, and credits are what a run costs once your free runs for the day are gone -- 1 credit for a small run or 5 for a large one.
| Parameter | Type | Description |
|---|---|---|
| credits * | integer | How many credits to buy: at least 1 and at most 100 in one call. |
{
"name": "buy_credits",
"title": "Buy Neumann credits with your saved card",
"description": "Charges the payment card saved on the user's account to buy Neumann credits; without a saved card it charges nothing and returns a checkout link instead. One call buys at most 100 credits ($50.00 at today's price); a request for more is refused and charges nothing. When the user asks for more than that, do not call it yet: tell them the limit and ask how many to buy now. A second purchase needs the user's agreement again. Credits pay for runs once the free runs for the day are used up, or for a model too large to run free. Use this when an account is low on credits and the user has agreed to the purchase; to see the balance and the live price first, call check_account_and_credits. When no card is saved yet, it returns payment_status checkout_required and a checkout_url, which the user opens in a browser to save a card before you call this tool again. It returns the credits bought, the new balance, the payment status and, when a card is needed, the checkout_url. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. When you are signed in rather than using a key, the sign-in must include billing access (the neumann:billing scope); without it the call is refused with insufficient_scope and charges nothing, and the user signs in again to grant it. Cost: charges the payment card saved on your account for each credit, currently $0.50 per credit (check_account_and_credits shows the live price). It needs an account, and credits are what a run costs once your free runs for the day are gone -- 1 credit for a small run or 5 for a large one.",
"inputSchema": {
"type": "object",
"title": "BuyCreditsInput",
"required": [
"credits"
],
"properties": {
"credits": {
"type": "integer",
"title": "Credits",
"maximum": 100,
"minimum": 1,
"examples": [
20
],
"description": "How many credits to buy: at least 1 and at most 100 in one call."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "BuyCreditsResult",
"required": [
"credits_purchased",
"new_balance",
"payment_status"
],
"properties": {
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"new_balance": {
"type": "integer",
"title": "New Balance",
"description": "Credit balance after the purchase."
},
"checkout_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Checkout Url",
"default": null,
"description": "Set only when payment_status is checkout_required: a link for the user to open in a browser and save a card. Call buy_credits again afterwards to complete the purchase. Otherwise null."
},
"payment_status": {
"type": "string",
"title": "Payment Status",
"description": "The card payment's status, for example succeeded. checkout_required means no card was saved, so nothing was bought or charged; open checkout_url to save one."
},
"credits_purchased": {
"type": "integer",
"title": "Credits Purchased",
"description": "Credits added."
}
},
"description": "Result of the purchase."
},
"annotations": {
"title": "Buy Neumann credits with your saved card",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Creates a public web link to one of your results, so you can hand the numbers to someone who has no Neumann account. Use this when the user wants to send, publish or show a result to another person; to put the numbers in the conversation instead, call get_simulation_results. It works for any run you own: a run from run_monte_carlo_simulation, rank_inputs_by_impact or summarize_outcome_scenarios, and a run of a graph you saved. There is one share tool for every kind of run -- do not look for a separate one. Pass the run_id the run tool returned when the run was made, earlier in the conversation; no tool lists runs, and you do not need a graph_id. That holds for a run of a saved model too: when the user asks to share the run of a saved graph, call this tool directly with that run's run_id -- list_graphs and get_graph return graph_ids, not run_ids, so they are not a step here. Calling it again for the same run returns the same link rather than a second one. Anyone who has the link can open the result without signing in, so ask the user before you create one. delete_run deletes the stored result, which also stops its share link working. There is no way to turn off a link and keep the result. A run made without an account takes two calls, and the run_id is what carries it from one to the other. First call: the caller has no account, so call this tool with the run_id anyway; nothing is shared, and it returns a message asking the user to sign in with a free Kromatic account -- tell the user that. Second call: once the user has signed in, call this tool again with the SAME run_id. Only that second call shares the run and keeps it on the account; signing in alone shares nothing, and a different run_id, or a new run, does not carry the claim. Do it within 24 hours, because a run made without an account is deleted after that. When you tell the user what happens next, say both steps: sign in, then you will share it using the same run. It returns the share_url. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.
| Parameter | Type | Description |
|---|---|---|
| run_id * | string |
Saves a model to your Neumann account so you can come back to it instead of describing it again. A saved model is called a graph: its uncertain inputs, the formulas that combine them, and the links between them. Use this when the user will revisit this model -- a budget, a plan, a business case they will update -- or when you want to re-analyse it later without resending it; for a one-off question, pass the model inline to run_monte_carlo_simulation and save nothing. Omit graph_id to save a new graph. Pass the graph_id of a graph you saved before to replace that same graph with this version; the earlier versions are kept, so replacing is not losing anything. An input may be saved before it has a distribution, so you can build a draft model over a conversation; a graph with such an input cannot be run or analysed until each input has one. An input can also be given as an estimated range (estimate: worst, best, most likely) with a distribution_type and no params: the save fits the params to the range. Changing a saved input's range re-fits its params, and changing only its params works the range out again. If a range cannot be fitted, the error estimate_fit_failed names the input and nothing at all is saved: not that input, not the rest of the model, and a graph you were replacing keeps its last saved version. So after that error there is nothing new to read back with get_graph; tell the user which range could not be fitted and fix it. It returns the graph_id to use later, the version_id of the version it just stored, the name, and when it was last updated. Use that graph_id with get_graph to read the model back, with rank_inputs_by_impact or summarize_outcome_scenarios in place of an inline graph, and with delete_graph to remove it. run_monte_carlo_simulation does not take a graph_id: read the graph with get_graph and pass it inline. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.
| Parameter | Type | Description |
|---|---|---|
| name * | string | A short name the user will recognise later, shown by list_graphs. Use the user's own words for the thing being modelled. |
| graph |
Lists the graphs saved on your Neumann account, the most recently updated first. Use this when the user refers to a saved model that is not among the newest ones check_account_and_credits shows, or to page through all of them; it is how you find the id that get_graph, rank_inputs_by_impact, summarize_outcome_scenarios and delete_graph need. It does not list runs or results -- it lists the models themselves. It returns one entry per graph with its graph_id, name, when it was last updated and how many input and formula nodes it has, plus next_offset when there are more to page through. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many graphs to return, most recently updated first. |
| offset | integer | How many graphs to skip, for paging. Use the next_offset the previous call returned. |
{
"name": "list_graphs",
"title": "List the models saved on your account",
"description": "Lists the graphs saved on your Neumann account, the most recently updated first. Use this when the user refers to a saved model that is not among the newest ones check_account_and_credits shows, or to page through all of them; it is how you find the id that get_graph, rank_inputs_by_impact, summarize_outcome_scenarios and delete_graph need. It does not list runs or results -- it lists the models themselves. It returns one entry per graph with its graph_id, name, when it was last updated and how many input and formula nodes it has, plus next_offset when there are more to page through. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.",
"inputSchema": {
"type": "object",
"title": "ListGraphsInput",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 20,
"maximum": 100,
"minimum": 1,
"examples": [
20
],
"description": "How many graphs to return, most recently updated first."
},
"offset": {
"type": "integer",
"title": "Offset",
"default": 0,
"minimum": 0,
"examples": [
0
],
"description": "How many graphs to skip, for paging. Use the next_offset the previous call returned."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"GraphSummary": {
"type": "object",
"title": "GraphSummary",
"required": [
"graph_id",
"name",
"updated_at",
"root_node_count",
"calc_node_count"
],
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"graph_id": {
"type": "string",
"title": "Graph Id",
"description": "Pass this to get_graph or save_graph."
},
"updated_at": {
"type": "string",
"title": "Updated At",
"description": "ISO-8601 instant of the last save."
},
"calc_node_count": {
"type": "integer",
"title": "Calc Node Count"
},
"root_node_count": {
"type": "integer",
"title": "Root Node Count"
}
},
"description": "One row of a ``list_graphs`` result."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "ListGraphsResult",
"required": [
"graphs"
],
"properties": {
"graphs": {
"type": "array",
"items": {
"$ref": "#/$defs/GraphSummary"
},
"title": "Graphs",
"description": "One entry per saved graph, most recently updated first."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"next_offset": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Next Offset",
"default": null,
"description": "The offset to pass next to get the following page, or null when this was the last page."
}
},
"description": "The graphs saved on your account."
},
"annotations": {
"title": "List the models saved on your account",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Reads one graph you saved earlier, by its graph_id, and returns the whole model in the same shape the run tools accept; an input saved without a distribution comes back with distribution_type null and distribution_params {}. Use this when you want to show the user what is in a saved model, edit it before running it again, or run it with run_monte_carlo_simulation, which takes the model inline and not a graph_id. To find a graph_id first, call list_graphs. It returns the graph_id, the name, when it was last updated, and the graph itself: its uncertain inputs with their distributions, the formula nodes, the links between them and the run settings. It reads the model, not any result of running it. After a save_graph error there is nothing new to read: a failed save stores nothing. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.
| Parameter | Type | Description |
|---|---|---|
| graph_id * | string | Which saved graph to read, from save_graph or list_graphs. |
{
"name": "get_graph",
"title": "Read a model you saved",
"description": "Reads one graph you saved earlier, by its graph_id, and returns the whole model in the same shape the run tools accept; an input saved without a distribution comes back with distribution_type null and distribution_params {}. Use this when you want to show the user what is in a saved model, edit it before running it again, or run it with run_monte_carlo_simulation, which takes the model inline and not a graph_id. To find a graph_id first, call list_graphs. It returns the graph_id, the name, when it was last updated, and the graph itself: its uncertain inputs with their distributions, the formula nodes, the links between them and the run settings. It reads the model, not any result of running it. After a save_graph error there is nothing new to read: a failed save stores nothing. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.",
"inputSchema": {
"type": "object",
"title": "GetGraphInput",
"required": [
"graph_id"
],
"properties": {
"graph_id": {
"type": "string",
"title": "Graph Id",
"examples": [
"8f3c2a"
],
"description": "Which saved graph to read, from save_graph or list_graphs."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "GetGraphResult",
"required": [
"graph_id",
"name",
"updated_at",
"graph"
],
"properties": {
"name": {
"type": "string",
"title": "Name",
"description": "The name this graph is saved under."
},
"graph": {
"type": "object",
"description": "The model itself, in the shape the run tools accept, except that an input saved without a distribution comes back with distribution_type null and distribution_params {}; such a graph cannot be run until you give that input a distribution. Each input comes back with its estimate (the range) beside its distribution_params; estimate.origin says whether the range was stated or worked out from the params. Edit it and pass it back to run_monte_carlo_simulation, or save the edited version with save_graph and this graph_id. Its full schema is run_monte_carlo_simulation's graph parameter."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"graph_id": {
"type": "string",
"title": "Graph Id",
"description": "The id of the graph that was read."
},
"updated_at": {
"type": "string",
"title": "Updated At",
"description": "When this graph was last saved, as an ISO-8601 time."
}
},
"description": "The saved graph."
},
"annotations": {
"title": "Read a model you saved",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Deletes one graph you saved, together with the runs of it. Use this when the user has explicitly asked for that model to be removed, and not otherwise. Confirm which one first with list_graphs or get_graph, because the graph_id is the only thing that says which model goes. Deletion is final as soon as this returns: nothing can restore it, through any tool or any request, so do not tell the user it can be recovered. Neumann clears the stored data within 30 days. Deleting the same graph twice changes nothing and does not extend the 30 days. To stop using a graph without removing it, just leave it saved and do not pass its graph_id. It returns the graph_id, what kind of thing was deleted, the time it was deleted and the date it is purged for good. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.
| Parameter | Type | Description |
|---|---|---|
| graph_id * | string | Which saved graph to delete, from list_graphs. Its runs go with it. Confirm with the user first: no tool here can put it back. |
{
"name": "delete_graph",
"title": "Delete a model you saved",
"description": "Deletes one graph you saved, together with the runs of it. Use this when the user has explicitly asked for that model to be removed, and not otherwise. Confirm which one first with list_graphs or get_graph, because the graph_id is the only thing that says which model goes. Deletion is final as soon as this returns: nothing can restore it, through any tool or any request, so do not tell the user it can be recovered. Neumann clears the stored data within 30 days. Deleting the same graph twice changes nothing and does not extend the 30 days. To stop using a graph without removing it, just leave it saved and do not pass its graph_id. It returns the graph_id, what kind of thing was deleted, the time it was deleted and the date it is purged for good. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.",
"inputSchema": {
"type": "object",
"title": "DeleteGraphInput",
"required": [
"graph_id"
],
"properties": {
"graph_id": {
"type": "string",
"title": "Graph Id",
"examples": [
"8f3c2a"
],
"description": "Which saved graph to delete, from list_graphs. Its runs go with it. Confirm with the user first: no tool here can put it back."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "DeleteGraphResult",
"required": [
"graph_id",
"deleted_at",
"purge_after"
],
"properties": {
"kind": {
"type": "string",
"const": "graph",
"title": "Kind",
"default": "graph",
"description": "What kind of thing was deleted: a graph."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"graph_id": {
"type": "string",
"title": "Graph Id",
"description": "The id of the graph that was deleted."
},
"deleted_at": {
"type": "string",
"title": "Deleted At",
"description": "When it was deleted, as an ISO-8601 time."
},
"purge_after": {
"type": "string",
"title": "Purge After",
"description": "The ISO-8601 instant by which the stored data is cleared. The deletion is already final; this date is not a recovery window."
}
},
"description": "What was deleted."
},
"annotations": {
"title": "Delete a model you saved",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}Deletes one of your own runs -- one result -- and its share link, leaving the model it came from alone. It works on any run_id you can read, whether the run came from a model you passed inline or from one you saved; afterwards get_simulation_results can no longer read it. Use this when the user has explicitly asked for that result to be removed, and not otherwise. To remove a saved model and all of its runs at once, use delete_graph. Deletion is final as soon as this returns: nothing can restore it, through any tool or any request, so do not tell the user it can be recovered. Neumann clears the stored data within 30 days. Deleting the same run twice changes nothing and does not extend the 30 days. It returns the run_id, what kind of thing was deleted, the time it was deleted and the date it is purged for good. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.
| Parameter | Type | Description |
|---|---|---|
| run_id * | string | Which run to delete, as returned by any run tool. The model it came from is left alone. Confirm with the user first: no tool here can put it back. |
{
"name": "delete_run",
"title": "Delete a result you saved",
"description": "Deletes one of your own runs -- one result -- and its share link, leaving the model it came from alone. It works on any run_id you can read, whether the run came from a model you passed inline or from one you saved; afterwards get_simulation_results can no longer read it. Use this when the user has explicitly asked for that result to be removed, and not otherwise. To remove a saved model and all of its runs at once, use delete_graph. Deletion is final as soon as this returns: nothing can restore it, through any tool or any request, so do not tell the user it can be recovered. Neumann clears the stored data within 30 days. Deleting the same run twice changes nothing and does not extend the 30 days. It returns the run_id, what kind of thing was deleted, the time it was deleted and the date it is purged for good. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.",
"inputSchema": {
"type": "object",
"title": "DeleteRunInput",
"required": [
"run_id"
],
"properties": {
"run_id": {
"type": "string",
"title": "Run Id",
"examples": [
"run_8f3c2a"
],
"description": "Which run to delete, as returned by any run tool. The model it came from is left alone. Confirm with the user first: no tool here can put it back."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "DeleteRunResult",
"required": [
"run_id",
"deleted_at",
"purge_after"
],
"properties": {
"kind": {
"type": "string",
"const": "run",
"title": "Kind",
"default": "run",
"description": "What kind of thing was deleted: a run."
},
"run_id": {
"type": "string",
"title": "Run Id",
"description": "The id of the run that was deleted."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"deleted_at": {
"type": "string",
"title": "Deleted At",
"description": "When it was deleted, as an ISO-8601 time."
},
"purge_after": {
"type": "string",
"title": "Purge After",
"description": "The ISO-8601 instant by which the stored data is cleared. The deletion is already final; this date is not a recovery window."
}
},
"description": "What was deleted."
},
"annotations": {
"title": "Delete a result you saved",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}Neumann runs Monte Carlo simulations of a model, so you get a realistic range of outcomes and their odds instead of one guessed number. Use it for any plan built on uncertain numbers: project cost and budget estimates (including three-point low / most likely / high estimates per line item), schedules and delivery dates, capacity and staffing, revenue and growth, and investment returns such as NPV, IRR and payback. It does not fetch live data (prices, exchange rates) or invent the input ranges: you or another source supply them. A model is a set of uncertain inputs (each drawn from a probability distribution), the formulas that combine them, and the links between them. One simulation of a model is a run. A run is made of many trials, and each trial is one random draw of every input. Typical flow: 1. Build the model. Every input needs a distribution before the model can run, and a "between X and Y" guess is not one: use convert_range_to_distribution to turn such a guess into an input's distribution parameters. Use convert_distribution_to_range to read existing parameters back as a range. 2. Optionally call check_simulation_model to find mistakes (it takes the model inline; for a saved model, read it with get_graph first), and estimate_simulation_size_and_cost to see size and credit cost. Both are free. 3. Call run_monte_carlo_simulation for the full distribution of outcomes: the 10th to 90th percentiles, NPV, IRR, payback, or the chance of beating a target or staying within a budget. Call summarize_outcome_scenarios for worst, median and best values, or for any other percentile, such as the P80 total cost or the P95 finish date. Call rank_inputs_by_impact to find which inputs matter most (a one-at-a-time sensitivity analysis, shown as a tornado chart). Each returns a short summary and a run_id. A run that takes longer than about 40 seconds keeps running in the background and returns status running instead. 4. Call get_simulation_results with the run_id to wait for a running run (each call waits up to 30 seconds and reports percent done; repeat until status is completed), or to get specific numbers from a finished run: other nodes or periods, any percentile, the chance of reaching a threshold, or a histogram. 5. Keep, share or delete. save_graph stores a model on your account so you can come back to it; it saves the model, not a result, and runs nothing. With an account, check_account_and_credits shows how many models are saved and the three most recently updated, with their graph_ids; list_graphs lists all of them, and get_graph returns the model itself. To run a saved model, pass what get_graph returns to run_monte_carlo_simulation, which does not take a graph_id; rank_inputs_by_impact and summarize_outcome_scenarios also accept a graph_id directly. A saved model with an input that has no distribution yet can be saved and read, but a run or analysis of it is refused with incomplete_model, which costs nothing and needs no balance check; give each such input a distribution, save again with the same graph_id, then run. To hand a result to someone without a Neumann account, call create_result_share_link with its run_id: one tool for every kind of run, and anyone with the link can open the result, so ask the user first. delete_graph deletes a saved model and every run of it; delete_run deletes one result, with its share link, and leaves the model. No tool here revokes a share link: delete_run is not a revocation control, because it deletes the result itself. Delete only when the user asks: no tool here can undo a delete. save_graph, list_graphs, get_graph, create_result_share_link, delete_graph and delete_run debit no credits and spend no free daily runs, but each needs an account; check_account_and_credits needs none. What a run costs depends on how you connect -- three ways, and only the second has free runs of your own: - No account. 3 free runs per UTC day, each model up to 1,000 trials and 20 nodes. A caller without an accoun
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
| Description |
|---|
| seed | any | Optional whole number that fixes the random draws, so repeating the call gives the same result. Exact repeats are guaranteed only for small runs, where trials × nodes × time periods is at most 100,000. |
| graph | object | The model: root_nodes (uncertain inputs), calc_nodes (formulas), edges (links; formulas refer to them like {e1}) and run_params (trials and time periods). Same format as run_monte_carlo_simulation's graph, which documents formulas, periods, distributions and financial metrics in full. Give this or g… |
| detail | string | How much to return. summary (the default): one row per input with its rank, its low and high values, the outcome at each, the swing between them and its elasticity. full: also each input's whole response curve. |
| graph_id | any | The id of a graph you already saved, to analyse that graph instead of sending it inline. Give this or graph, not both. Requires a Neumann account -- an anonymous caller must use graph instead. If an input in the saved graph has no distribution yet, the call is refused with incomplete_model, which li… |
| quantiles | any | A list of points in each input's own distribution to try. Each point is a fraction from 0 to 1 naming a percentile: 0.05 is the 5th percentile, the value 5% of outcomes fall below. Default [0.05, 0.5, 0.95]. Give this or num_quantiles, not both. |
| time_period | any | Index of the time period to measure, counting from 0: with 12 monthly periods, 11 is month 12. Defaults to the last period. This measures the node's value in that one period, not a total. For a cumulative figure such as year-one profit, add a running-total calc node with formula {e1} + {e2}, where e… |
| num_quantiles | any | Instead of quantiles: how many points to try, an even whole number from 2 to 10. That many percentiles are spread evenly between the 5th and 95th, and the median (0.5) is added. 2 gives [0.05, 0.5, 0.95]; 4 gives [0.05, 0.275, 0.5, 0.725, 0.95]. |
| target_node_id | any | The id of the outcome node to measure. Defaults to the last calc node in the model, which is usually the final outcome. |
{
"name": "rank_inputs_by_impact",
"title": "Rank which inputs drive an outcome most (one-at-a-time sensitivity)",
"description": "Ranks a model's uncertain inputs by how much each one moves a chosen outcome, and returns the data for a tornado chart (a bar chart with one horizontal bar per input, the biggest swing at the top). This is a one-at-a-time (OAT) sensitivity analysis: it shows how much the outcome changes when each input changes on its own. Every input is held at its median while one input at a time is set to low, middle and high values from its own distribution (by default its 5th, 50th and 95th percentiles). The tool records how the outcome's average changes. Use this when you need to know which assumption matters most, so you know what to research or de-risk first. It returns one entry per input, ranked so rank 1 has the biggest impact. Each entry lists the input values tried, the outcome at each, and an elasticity score. Elasticity is about how many percent the outcome's average moves when the input moves 1 percent, averaged over the values tried. It is never negative: it says how much an input matters, not which way it pushes the outcome; to see the direction, compare the outcome at the input's low and high values. It returns numbers, not an image. Inputs whose distribution produces a list of values are skipped. It always returns a run_id. It runs the model once per input per value tried, so on a big model it can take minutes: if it is not done in about 40 seconds you get status running, and get_simulation_results gives you progress and then the ranking. Cost: it counts as one run per call, however many times it runs the model inside, and it is charged only if the analysis succeeds. Without an account, 1 of your 3 free runs per UTC day, for a model up to 1,000 trials and 20 nodes; that daily allowance is counted per network address and client, so on a shared platform such as Claude.ai or ChatGPT you may find today's free runs already spent by someone else. Signed in with a free Kromatic account, 1 of 10 free runs per UTC day, for a small model (trials x nodes x periods at most 100,000, and within 10,000 trials and 50 nodes), spent before any credits. Beyond that, 1 credit for a small model or 5 for a large one, currently $0.50 per credit; buy_credits tops up. A model that is invalid, or over the limits of the tier you are in, is rejected before running and costs nothing, and so is a saved graph refused with incomplete_model: no credit, no free run, no run recorded. If the analysis fails partway through, it depends on what paid for it: without an account the free run is used up and not given back; a signed-in free run is given back; credits are not charged.",
"inputSchema": {
"type": "object",
"title": "RankInputsByImpactInput",
"properties": {
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"default": null,
"description": "Optional whole number that fixes the random draws, so repeating the call gives the same result. Exact repeats are guaranteed only for small runs, where trials × nodes × time periods is at most 100,000."
},
"graph": {
"type": "object",
"examples": [
{
"edges": [
{
"id": "e1",
"source": "customers",
"target": "revenue"
},
{
"id": "e2",
"source": "price",
"target": "revenue"
}
],
"calc_nodes": [
{
"id": "revenue",
"name": "Monthly revenue",
"formula": "{e1} * {e2}"
}
],
"root_nodes": [
{
"id": "customers",
"name": "Customers per month",
"distribution_type": "normal",
"distribution_params": {
"std": 200,
"mean": 1000
}
},
{
"id": "price",
"name": "Price (USD)",
"distribution_type": "triangle",
"distribution_params": {
"max_val": 15,
"min_val": 8,
"mode_val": 10
}
}
],
"run_params": {
"trials": 1000,
"time_periods": 12
}
}
],
"description": "The model: root_nodes (uncertain inputs), calc_nodes (formulas), edges (links; formulas refer to them like {e1}) and run_params (trials and time periods). Same format as run_monte_carlo_simulation's graph, which documents formulas, periods, distributions and financial metrics in full. Give this or graph_id, not both. Only this outline is published here: the full schema is on run_monte_carlo_simulation's graph parameter, and the neumann://catalog resource lists every distribution and formula function. Neumann checks the model against that full schema when you call this tool and names any problem."
},
"detail": {
"enum": [
"summary",
"full"
],
"type": "string",
"title": "Detail",
"default": "summary",
"description": "How much to return. summary (the default): one row per input with its rank, its low and high values, the outcome at each, the swing between them and its elasticity. full: also each input's whole response curve."
},
"graph_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Graph Id",
"default": null,
"description": "The id of a graph you already saved, to analyse that graph instead of sending it inline. Give this or graph, not both. Requires a Neumann account -- an anonymous caller must use graph instead. If an input in the saved graph has no distribution yet, the call is refused with incomplete_model, which lists those inputs. The refusal costs nothing (no credit or free run is spent and no run is recorded), so there is no need to check your balance: give each one a distribution, save the graph again under the same id, and try again."
},
"quantiles": {
"anyOf": [
{
"type": "array",
"items": {
"type": "number"
}
},
{
"type": "null"
}
],
"title": "Quantiles",
"default": null,
"examples": [
[
0.1,
0.5,
0.9
]
],
"description": "A list of points in each input's own distribution to try. Each point is a fraction from 0 to 1 naming a percentile: 0.05 is the 5th percentile, the value 5% of outcomes fall below. Default [0.05, 0.5, 0.95]. Give this or num_quantiles, not both."
},
"time_period": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Time Period",
"default": null,
"description": "Index of the time period to measure, counting from 0: with 12 monthly periods, 11 is month 12. Defaults to the last period. This measures the node's value in that one period, not a total. For a cumulative figure such as year-one profit, add a running-total calc node with formula {e1} + {e2}, where e1 brings in the per-period value and e2 is an edge from the running-total node to itself with delay 1. Then target that node at index 11. This delayed self-edge is allowed; only loops with no delay are errors. In run_monte_carlo_simulation, use a cumsum metric instead."
},
"num_quantiles": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Num Quantiles",
"default": null,
"description": "Instead of quantiles: how many points to try, an even whole number from 2 to 10. That many percentiles are spread evenly between the 5th and 95th, and the median (0.5) is added. 2 gives [0.05, 0.5, 0.95]; 4 gives [0.05, 0.275, 0.5, 0.725, 0.95]."
},
"target_node_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Target Node Id",
"default": null,
"examples": [
"revenue"
],
"description": "The id of the outcome node to measure. Defaults to the last calc node in the model, which is usually the final outcome."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"TornadoRow": {
"type": "object",
"title": "TornadoRow",
"required": [
"rank",
"input_id",
"baseline_input",
"low_input",
"high_input",
"outcome_at_low",
"outcome_at_high",
"swing",
"elasticity"
],
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name",
"default": null
},
"rank": {
"type": "integer",
"title": "Rank",
"description": "1 = the input with the biggest impact."
},
"swing": {
"type": "number",
"title": "Swing",
"description": "abs(outcome_at_high - outcome_at_low): the bar's length."
},
"input_id": {
"type": "string",
"title": "Input Id"
},
"low_input": {
"type": "number",
"title": "Low Input",
"description": "The input at the lowest percentile tried."
},
"elasticity": {
"type": "number",
"title": "Elasticity",
"description": "Roughly the % change in the outcome per 1% change in the input (unsigned)."
},
"high_input": {
"type": "number",
"title": "High Input",
"description": "The input at the highest percentile tried."
},
"baseline_input": {
"type": "number",
"title": "Baseline Input",
"description": "The input's median, where it is held otherwise."
},
"outcome_at_low": {
"type": "number",
"title": "Outcome At Low",
"description": "The outcome's mean with the input at low_input."
},
"outcome_at_high": {
"type": "number",
"title": "Outcome At High",
"description": "The outcome's mean with the input at high_input."
}
},
"description": "One input's bar in the tornado chart."
},
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"RunProgress": {
"type": "object",
"title": "RunProgress",
"required": [
"percent",
"done",
"total",
"unit"
],
"properties": {
"done": {
"type": "integer",
"title": "Done"
},
"unit": {
"enum": [
"trials",
"runs"
],
"type": "string",
"title": "Unit",
"description": "trials for a simulation; runs (internal simulations) for a sensitivity sweep."
},
"total": {
"type": "integer",
"title": "Total"
},
"percent": {
"type": "number",
"title": "Percent",
"description": "0 to 100."
}
},
"description": "How far a queued or running run has got."
},
"TargetOutput": {
"type": "object",
"title": "TargetOutput",
"required": [
"node_id",
"time_period",
"baseline_value",
"response_curve",
"elasticity",
"rank"
],
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name",
"default": null
},
"rank": {
"type": "integer",
"title": "Rank",
"description": "1 for the input with the biggest impact."
},
"node_id": {
"type": "string",
"title": "Node Id"
},
"elasticity": {
"type": "number",
"title": "Elasticity",
"description": "How strongly the outcome reacts: about the percent change in the outcome's average per 1% change in the input, averaged over the values tried. Never negative, so it shows how much the input matters, not the direction; compare the response_curve outcomes at low and high for that. Larger means more impact."
},
"time_period": {
"type": "integer",
"title": "Time Period"
},
"baseline_value": {
"type": "number",
"title": "Baseline Value",
"description": "Outcome mean with every input at its median."
},
"response_curve": {
"type": "array",
"items": {
"$ref": "#/$defs/ResponseCurvePoint"
},
"title": "Response Curve"
}
},
"description": "How the outcome responded to this input."
},
"InputVariable": {
"type": "object",
"title": "InputVariable",
"required": [
"type",
"id",
"baseline_value"
],
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name",
"default": null
},
"type": {
"type": "string",
"title": "Type"
},
"baseline_value": {
"type": "number",
"title": "Baseline Value",
"description": "The input's median, where it is held while other inputs vary."
}
},
"description": "The input that was varied."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
},
"SensitivityResult": {
"type": "object",
"title": "SensitivityResult",
"required": [
"input_variable",
"target_output"
],
"properties": {
"target_output": {
"$ref": "#/$defs/TargetOutput"
},
"input_variable": {
"$ref": "#/$defs/InputVariable"
}
},
"description": "One input's entry: the input and how the outcome responded."
},
"ResponseCurvePoint": {
"type": "object",
"title": "ResponseCurvePoint",
"required": [
"quantile",
"input_value",
"output_value",
"delta_output",
"sensitivity"
],
"properties": {
"quantile": {
"type": "number",
"title": "Quantile"
},
"input_value": {
"type": "number",
"title": "Input Value"
},
"sensitivity": {
"type": "number",
"title": "Sensitivity"
},
"delta_output": {
"type": "number",
"title": "Delta Output"
},
"output_value": {
"type": "number",
"title": "Output Value"
}
},
"description": "One tried value: the percentile, the input value, the outcome mean, the change from the outcome with every input at its median, and the local sensitivity."
}
},
"title": "RankInputsByImpactResult",
"required": [
"target_node_id",
"time_period",
"quantiles",
"runs_executed"
],
"properties": {
"run_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Run Id",
"default": null
},
"status": {
"enum": [
"completed",
"running",
"queued"
],
"type": "string",
"title": "Status",
"default": "completed"
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"results": {
"type": "array",
"items": {
"$ref": "#/$defs/SensitivityResult"
},
"title": "Results",
"description": "One entry per input, in rank order (rank 1 = biggest impact)."
},
"tornado": {
"type": "array",
"items": {
"$ref": "#/$defs/TornadoRow"
},
"title": "Tornado"
},
"progress": {
"anyOf": [
{
"$ref": "#/$defs/RunProgress"
},
{
"type": "null"
}
],
"default": null,
"description": "Present while the run is queued or running."
},
"next_step": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Next Step",
"default": null,
"description": "What to do next while the run is still going."
},
"quantiles": {
"type": "array",
"items": {
"type": "number"
},
"title": "Quantiles",
"description": "The percentiles of each input that were tried, as fractions."
},
"time_period": {
"type": "integer",
"title": "Time Period",
"description": "The period measured (index counted from 0)."
},
"runs_executed": {
"type": "integer",
"title": "Runs Executed",
"description": "Internal simulation runs used: 1 baseline plus inputs × quantiles. You are billed once."
},
"target_node_id": {
"type": "string",
"title": "Target Node Id",
"description": "The outcome node measured."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits charged (0 without an account)."
},
"baseline_outcome": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Baseline Outcome",
"default": null,
"description": "The outcome's mean with every input at its median."
},
"inputs_not_shown": {
"type": "integer",
"title": "Inputs Not Shown",
"default": 0
},
"estimated_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Estimated Seconds",
"default": null,
"description": "Rough total run time, in seconds."
}
},
"description": "Inputs ranked by impact on the outcome: the data for a tornado chart."
},
"annotations": {
"title": "Rank which inputs drive an outcome most (one-at-a-time sensitivity)",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}| graph | object | The model: root_nodes (uncertain inputs), calc_nodes (formulas), edges (links; formulas refer to them like {e1}) and run_params (trials and time periods). Same format as run_monte_carlo_simulation's graph, which documents formulas, periods, distributions and financial metrics in full. Give this or g… |
| graph_id | any | The id of a graph you already saved, to analyse that graph instead of sending it inline. Give this or graph, not both. Requires a Neumann account -- an anonymous caller must use graph instead. If an input in the saved graph has no distribution yet, the call is refused with incomplete_model, which li… |
| percentiles | any | A list of percentiles of the outcome to report. Each is a fraction from 0 to 1: 0.1 is the 10th percentile, the value 10% of trials fall below. Default [0, 0.5, 1]: 0 is the lowest trial (labelled worst), 0.5 the median, and 1 the highest trial (labelled best). Other values are labelled like p10 (10… |
| time_period | any | Index of the time period to measure, counting from 0: with 12 monthly periods, 11 is month 12. Defaults to the last period. This measures the node's value in that one period, not a total. For a cumulative figure such as year-one profit, add a running-total calc node with formula {e1} + {e2}, where e… |
| target_node_id | any | The id of the outcome node to measure. Defaults to the last calc node in the model, which is usually the final outcome. |
{
"name": "summarize_outcome_scenarios",
"title": "Summarize worst, median and best outcomes",
"description": "Reports one outcome's worst, median and best cases from one run of a model. By default, worst is the lowest value in any trial, median is the middle value, and best is the highest value. Those labels assume higher is better. For a cost or a duration, where lower is better, swap them when you tell the user: the scenario labelled worst is the cheapest or fastest case, which is the good outcome, and the one labelled best is the most expensive or slowest. You can ask for other percentiles instead, such as the 10th and 90th, or the 80th for a P80 total. Use this when you want a short worst, typical and best case story. For the range or the odds of outcomes (what range it could land in, how likely something is), use run_monte_carlo_simulation instead; to find which input matters most, use rank_inputs_by_impact. It takes the model inline in graph, or a saved model by graph_id directly, so you do not need get_graph first. If an input in the saved graph has no distribution yet, the call is refused with incomplete_model and costs nothing. It returns each scenario's outcome value and every input's own value at the same percentile of that input's distribution. Those input values are an estimate, not the exact inputs of that trial. It also returns a run_id; a long run comes back as status running, and get_simulation_results gives you progress and then the result. Cost: without an account, 1 of your 3 free runs per UTC day, for a model up to 1,000 trials and 20 nodes; that daily allowance is counted per network address and client, so on a shared platform such as Claude.ai or ChatGPT you may find today's free runs already spent by someone else. Signed in with a free Kromatic account, 1 of 10 free runs per UTC day, for a small model (trials x nodes x periods at most 100,000, and within 10,000 trials and 50 nodes), spent before any credits. Beyond that -- a larger model, or a day whose free runs are used up -- 1 credit for a small run or 5 for a large one, currently $0.50 per credit; buy_credits tops up. A model that is invalid, or over the limits of the tier you are in, is rejected before running and costs nothing. If it fails mid-run, it depends on the tier: without an account the free run is still used up and not given back; signed in on a free run, the free run is given back; on credits, you are not charged.",
"inputSchema": {
"type": "object",
"title": "SummarizeOutcomeScenariosInput",
"properties": {
"seed": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Seed",
"default": null,
"description": "Optional whole number that fixes the random draws, so repeating the call gives the same result. Exact repeats are guaranteed only for small runs, where trials × nodes × time periods is at most 100,000."
},
"graph": {
"type": "object",
"examples": [
{
"edges": [
{
"id": "e1",
"source": "customers",
"target": "revenue"
},
{
"id": "e2",
"source": "price",
"target": "revenue"
}
],
"calc_nodes": [
{
"id": "revenue",
"name": "Monthly revenue",
"formula": "{e1} * {e2}"
}
],
"root_nodes": [
{
"id": "customers",
"name": "Customers per month",
"distribution_type": "normal",
"distribution_params": {
"std": 200,
"mean": 1000
}
},
{
"id": "price",
"name": "Price (USD)",
"distribution_type": "triangle",
"distribution_params": {
"max_val": 15,
"min_val": 8,
"mode_val": 10
}
}
],
"run_params": {
"trials": 1000,
"time_periods": 12
}
}
],
"description": "The model: root_nodes (uncertain inputs), calc_nodes (formulas), edges (links; formulas refer to them like {e1}) and run_params (trials and time periods). Same format as run_monte_carlo_simulation's graph, which documents formulas, periods, distributions and financial metrics in full. Give this or graph_id, not both. Only this outline is published here: the full schema is on run_monte_carlo_simulation's graph parameter, and the neumann://catalog resource lists every distribution and formula function. Neumann checks the model against that full schema when you call this tool and names any problem."
},
"graph_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Graph Id",
"default": null,
"description": "The id of a graph you already saved, to analyse that graph instead of sending it inline. Give this or graph, not both. Requires a Neumann account -- an anonymous caller must use graph instead. If an input in the saved graph has no distribution yet, the call is refused with incomplete_model, which lists those inputs. The refusal costs nothing (no credit or free run is spent and no run is recorded), so there is no need to check your balance: give each one a distribution, save the graph again under the same id, and try again."
},
"percentiles": {
"anyOf": [
{
"type": "array",
"items": {
"type": "number"
}
},
{
"type": "null"
}
],
"title": "Percentiles",
"default": null,
"examples": [
[
0.1,
0.5,
0.9
]
],
"description": "A list of percentiles of the outcome to report. Each is a fraction from 0 to 1: 0.1 is the 10th percentile, the value 10% of trials fall below. Default [0, 0.5, 1]: 0 is the lowest trial (labelled worst), 0.5 the median, and 1 the highest trial (labelled best). Other values are labelled like p10 (10th percentile). Values between 0 and 1 are estimated from a histogram. The labels assume higher is better: for a cost or a duration, 'worst' is the lowest (cheapest or fastest) trial, so ask for percentiles such as 0.1 and 0.9 and read them as low and high."
},
"time_period": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Time Period",
"default": null,
"description": "Index of the time period to measure, counting from 0: with 12 monthly periods, 11 is month 12. Defaults to the last period. This measures the node's value in that one period, not a total. For a cumulative figure such as year-one profit, add a running-total calc node with formula {e1} + {e2}, where e1 brings in the per-period value and e2 is an edge from the running-total node to itself with delay 1. Then target that node at index 11. This delayed self-edge is allowed; only loops with no delay are errors. In run_monte_carlo_simulation, use a cumsum metric instead."
},
"target_node_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Target Node Id",
"default": null,
"examples": [
"revenue"
],
"description": "The id of the outcome node to measure. Defaults to the last calc node in the model, which is usually the final outcome."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"RunProgress": {
"type": "object",
"title": "RunProgress",
"required": [
"percent",
"done",
"total",
"unit"
],
"properties": {
"done": {
"type": "integer",
"title": "Done"
},
"unit": {
"enum": [
"trials",
"runs"
],
"type": "string",
"title": "Unit",
"description": "trials for a simulation; runs (internal simulations) for a sensitivity sweep."
},
"total": {
"type": "integer",
"title": "Total"
},
"percent": {
"type": "number",
"title": "Percent",
"description": "0 to 100."
}
},
"description": "How far a queued or running run has got."
},
"DrivingInput": {
"type": "object",
"title": "DrivingInput",
"required": [
"node_id",
"value"
],
"properties": {
"value": {
"type": "number",
"title": "Value",
"description": "The input's value at the scenario's percentile of its own distribution. An estimate, not the exact input of that trial."
},
"node_id": {
"type": "string",
"title": "Node Id"
}
},
"description": "One input's own value at the same percentile."
},
"ScenarioCase": {
"type": "object",
"title": "ScenarioCase",
"required": [
"label",
"percentile",
"output_value"
],
"properties": {
"label": {
"type": "string",
"title": "Label",
"description": "worst (lowest trial), median, best (highest trial), or p<N> for other percentiles."
},
"percentile": {
"type": "number",
"title": "Percentile"
},
"output_value": {
"type": "number",
"title": "Output Value",
"description": "The outcome at this percentile. Exact for the lowest and highest trial; estimated from a histogram in between."
},
"driving_inputs": {
"type": "array",
"items": {
"$ref": "#/$defs/DrivingInput"
},
"title": "Driving Inputs"
}
},
"description": "One scenario: the outcome at a percentile and each input's value at that percentile."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "SummarizeOutcomeScenariosResult",
"required": [
"target_node_id",
"time_period",
"trials",
"runs_executed"
],
"properties": {
"run_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Run Id",
"default": null
},
"status": {
"enum": [
"completed",
"running",
"queued"
],
"type": "string",
"title": "Status",
"default": "completed"
},
"trials": {
"type": "integer",
"title": "Trials",
"description": "Number of trials in the run."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"progress": {
"anyOf": [
{
"$ref": "#/$defs/RunProgress"
},
{
"type": "null"
}
],
"default": null,
"description": "Present while the run is queued or running."
},
"next_step": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Next Step",
"default": null,
"description": "What to do next while the run is still going."
},
"scenarios": {
"type": "array",
"items": {
"$ref": "#/$defs/ScenarioCase"
},
"title": "Scenarios",
"description": "One entry per percentile, lowest first."
},
"time_period": {
"type": "integer",
"title": "Time Period",
"description": "The period measured (index counted from 0)."
},
"runs_executed": {
"type": "integer",
"title": "Runs Executed",
"description": "Always 1; one run is reused for every scenario."
},
"target_node_id": {
"type": "string",
"title": "Target Node Id",
"description": "The outcome node measured."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits charged (0 without an account)."
},
"estimated_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Estimated Seconds",
"default": null,
"description": "Rough total run time, in seconds."
}
},
"description": "Outcome values at the requested percentiles, lowest first."
},
"annotations": {
"title": "Summarize worst, median and best outcomes",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}{
"name": "check_simulation_model",
"title": "Check a simulation model for errors before running it",
"description": "Checks a model you hold inline for mistakes, before you save or run it, and lists every problem it finds. It looks for loops with no delay, nodes that are not connected, unknown distributions, missing or invalid distribution parameters, and broken formulas. A loop, including an edge from a node to itself, is allowed and is not an error when at least one edge in it has delay 1 or more. Use this when you have built or edited a model and want to fix it without spending a run. It takes the model inline, not a graph_id: to check a saved model, read it with get_graph and pass what that returns. It does not run or rank anything, and it does not say what a run will cost (use estimate_simulation_size_and_cost for that). It returns is_valid and a list of issues. A draft input with no distribution yet (distribution_type null) is not rejected: it comes back as an issue with severity error naming that input, and is_valid is false, so the model is not ready to run until each such input has a distribution. You do not need this tool to learn that an input with only a low-high guess cannot run: it cannot, and convert_range_to_distribution turns the guess into a distribution. Each issue gives the rule broken, a severity (error, warning or info, where info is only a note), a message, and the node and edge ids involved. If an edge points at a node that does not exist, or the model is over your tier's size limit, you get an error message instead of the list. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs. Without an account, a model over 1,000 trials or 20 nodes is rejected, also at no cost.",
"inputSchema": {
"type": "object",
"title": "CheckSimulationModelInput",
"required": [
"graph"
],
"properties": {
"graph": {
"type": "object",
"examples": [
{
"edges": [
{
"id": "e1",
"source": "customers",
"target": "revenue"
},
{
"id": "e2",
"source": "price",
"target": "revenue"
}
],
"calc_nodes": [
{
"id": "revenue",
"name": "Monthly revenue",
"formula": "{e1} * {e2}"
}
],
"root_nodes": [
{
"id": "customers",
"name": "Customers per month",
"distribution_type": "normal",
"distribution_params": {
"std": 200,
"mean": 1000
}
},
{
"id": "price",
"name": "Price (USD)",
"distribution_type": "triangle",
"distribution_params": {
"max_val": 15,
"min_val": 8,
"mode_val": 10
}
}
],
"run_params": {
"trials": 1000,
"time_periods": 12
}
}
],
"description": "The model: root_nodes (uncertain inputs), calc_nodes (formulas), edges (links; formulas refer to them like {e1}) and run_params (trials and time periods). Same format as run_monte_carlo_simulation's graph, which documents formulas, periods, distributions and financial metrics in full. Unlike there, an input may have no distribution yet (distribution_type null, distribution_params {}): it is reported as an error, not rejected. Only this outline is published here: the full schema is on run_monte_carlo_simulation's graph parameter, and the neumann://catalog resource lists every distribution and formula function. Neumann checks the model against that full schema when you call this tool and names any problem."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
},
"ValidationIssue": {
"type": "object",
"title": "ValidationIssue",
"required": [
"rule",
"severity",
"message"
],
"properties": {
"rule": {
"type": "string",
"title": "Rule"
},
"edges": {
"type": "array",
"items": {
"type": "string"
},
"title": "Edges"
},
"nodes": {
"type": "array",
"items": {
"type": "string"
},
"title": "Nodes"
},
"message": {
"type": "string",
"title": "Message"
},
"severity": {
"type": "string",
"title": "Severity"
}
},
"description": "One problem: the rule broken, its severity (error, warning or info), a message, and the node and edge ids involved."
}
},
"title": "CheckSimulationModelResult",
"required": [
"is_valid"
],
"properties": {
"issues": {
"type": "array",
"items": {
"$ref": "#/$defs/ValidationIssue"
},
"title": "Issues"
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"is_valid": {
"type": "boolean",
"title": "Is Valid",
"description": "true when there are no errors. Warnings and info notes do not make it false."
}
},
"description": "Whether the model is ready to run, and every problem found."
},
"annotations": {
"title": "Check a simulation model for errors before running it",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}| percentile_range | number | A single fraction: the share of outcomes that should fall between the low and high ends, which is how sure you are. The default 0.9 means the middle 90%: a 5% chance of being below the low end and 5% above the high end. Mapping hedged words: "very sure" or "almost certainly" is about 0.9; "probably"… |
| distribution_type * | string | The distribution to fit. Which to pick: a rate or proportion between 0 and 1 (conversion, churn) → beta, with low and high given as fractions (2% is 0.02). A positive amount that can run high (revenue, price, deal size) → log_normal. A quantity equally likely to land above or below its middle → norm… |
{
"name": "convert_range_to_distribution",
"title": "Turn a min–max guess into distribution parameters",
"description": "Turns a low-to-high guess, such as \"between 80 and 120, 90% sure\", into the exact parameters a model input needs. A distribution is the shape of the uncertainty, for example normal (a bell curve), log_normal (skewed and never negative), triangle or uniform. The low and high values are the edges of the range you are that sure of, not hard limits. Use this when you have a rough estimate and need distribution parameters instead of guessing them: an input with only a low-high guess has no distribution yet and cannot run until it has one. You do not need it for a three-point low / most likely / high estimate: that goes straight into the model as a triangle input (min_val, mode_val, max_val), so call run_monte_carlo_simulation directly. Its reverse is convert_distribution_to_range. It returns the distribution type and its parameters, ready to use as a model input's distribution_params. The distribution_type parameter explains which type fits which kind of quantity. Supported types: normal, log_normal, uniform, triangle, beta, gamma, exponential, binomial, discrete_normal, discrete_lognormal, discrete_gamma, constant and bernoulli. Not supported: poisson, categorical, dirichlet, multivariate_normal and constant_array. For beta, give low and high as fractions (2% is 0.02). Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.",
"inputSchema": {
"type": "object",
"title": "ConvertRangeToDistributionInput",
"required": [
"distribution_type"
],
"properties": {
"max_estimate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Max Estimate",
"default": null,
"description": "The high end of your range. Required for every type except constant and bernoulli."
},
"min_estimate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Min Estimate",
"default": null,
"description": "The low end of your range. Required for every type except constant and bernoulli. Exponential ignores it, but a value must still be sent (any number works)."
},
"mode_estimate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Mode Estimate",
"default": null,
"description": "The most likely value. Required for constant (the fixed value), bernoulli (the chance of success, from 0 to 1) and binomial. For triangle it sets the peak; it must lie strictly between low and high, and defaults to their midpoint. For beta it is used as the peak when a fit allows, but the low and high ends take priority. Ignored by other types."
},
"percentile_range": {
"type": "number",
"title": "Percentile Range",
"default": 0.9,
"description": "A single fraction: the share of outcomes that should fall between the low and high ends, which is how sure you are. The default 0.9 means the middle 90%: a 5% chance of being below the low end and 5% above the high end. Mapping hedged words: \"very sure\" or \"almost certainly\" is about 0.9; \"probably\" is about 0.8; if unsure, ask the user. \"Could be higher\" means pick a right-skewed type such as log_normal, not a wider range.",
"exclusiveMaximum": 1,
"exclusiveMinimum": 0
},
"distribution_type": {
"type": "string",
"title": "Distribution Type",
"examples": [
"normal",
"log_normal"
],
"description": "The distribution to fit. Which to pick: a rate or proportion between 0 and 1 (conversion, churn) → beta, with low and high given as fractions (2% is 0.02). A positive amount that can run high (revenue, price, deal size) → log_normal. A quantity equally likely to land above or below its middle → normal. A value with hard limits you know → uniform (flat) or triangle (most likely value in between). A whole-number count (customers, units) → discrete_normal, discrete_lognormal or discrete_gamma, or binomial for successes out of a fixed number of attempts. Not supported here: poisson, categorical, dirichlet, multivariate_normal and constant_array."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "ConvertRangeToDistributionResult",
"required": [
"distribution_type",
"parameters",
"input"
],
"properties": {
"input": {
"type": "object",
"title": "Input",
"description": "Your inputs, echoed back.",
"additionalProperties": true
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"parameters": {
"type": "object",
"title": "Parameters",
"description": "The fitted parameters, for example {\"mean\": 100, \"std\": 12.2}.",
"additionalProperties": true
},
"distribution_type": {
"type": "string",
"title": "Distribution Type"
}
},
"description": "Fitted distribution parameters, ready to use as a model input's distribution_params."
},
"annotations": {
"title": "Turn a min–max guess into distribution parameters",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}| distribution_params * | object | The distribution's parameters, in the same form a model input uses, for example {"mean": 100, "std": 15} for normal or {"mu": 9.2, "sigma": 0.6} for log_normal. |
{
"name": "convert_distribution_to_range",
"title": "Turn distribution parameters into a min–max range",
"description": "Turns a distribution's parameters into the low and high ends of the range that holds a chosen share of outcomes, by default the middle 90%. It also gives the mean, median, mode, standard deviation and any percentiles you ask for. If you give a threshold, it gives the chance of landing below and above it. Use this when you have distribution parameters, from a model or from fermi (a companion forecasting server from Kromatic, the company behind Neumann, whose estimates carry next_steps.simulate.root_node), and want to know what they mean in plain numbers. Its reverse is convert_range_to_distribution, and the range it returns can be passed straight back to it. Values that do not apply, such as a uniform distribution's mode, come back as null with a note explaining why. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.",
"inputSchema": {
"type": "object",
"title": "ConvertDistributionToRangeInput",
"required": [
"distribution_type",
"distribution_params"
],
"properties": {
"quantiles": {
"anyOf": [
{
"type": "array",
"items": {
"type": "number",
"maximum": 1,
"minimum": 0
},
"minItems": 1
},
{
"type": "null"
}
],
"title": "Quantiles",
"default": null,
"examples": [
[
0.25,
0.5,
0.75
]
],
"description": "A list of percentiles to report. Each is a fraction from 0 to 1: 0.05 is the 5th percentile, the value 5% of outcomes fall below. No repeats. Default [0.05, 0.1, 0.5, 0.9, 0.95], returned under keys p5, p10, p50, p90 and p95."
},
"threshold": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Threshold",
"default": null,
"examples": [
15000
],
"description": "Optional value to compare against. The result gives the chance of being at or below it and the chance of being above it. For whole-number distributions it gives the chance of being below and above it, and notes the chance of landing exactly on it."
},
"percentile_range": {
"type": "number",
"title": "Percentile Range",
"default": 0.9,
"description": "A single fraction: the share of outcomes the returned range should hold, centred on the median. The default 0.9 means the middle 90%, so the range runs from the 5th to the 95th percentile.",
"exclusiveMaximum": 1,
"exclusiveMinimum": 0
},
"distribution_type": {
"type": "string",
"title": "Distribution Type",
"examples": [
"log_normal"
],
"description": "The distribution's name. Accepts every type a model input accepts: normal, log_normal, uniform, triangle, beta (values are fractions from 0 to 1), gamma, exponential, poisson, bernoulli, binomial, categorical, constant, discrete_normal, discrete_lognormal and discrete_gamma. categorical returns no range. dirichlet, multivariate_normal and constant_array produce lists of values, so every number comes back null. This is wider than convert_range_to_distribution, which cannot fit poisson or categorical."
},
"distribution_params": {
"type": "object",
"title": "Distribution Params",
"examples": [
{
"mu": 9.2,
"sigma": 0.6
},
{
"std": 15,
"mean": 100
}
],
"description": "The distribution's parameters, in the same form a model input uses, for example {\"mean\": 100, \"std\": 15} for normal or {\"mu\": 9.2, \"sigma\": 0.6} for log_normal.",
"additionalProperties": true
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"RangeInterval": {
"type": "object",
"title": "RangeInterval",
"required": [
"min_estimate",
"max_estimate",
"percentile_range"
],
"properties": {
"max_estimate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Max Estimate"
},
"min_estimate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Min Estimate"
},
"percentile_range": {
"type": "number",
"title": "Percentile Range"
}
},
"description": "Low and high ends of the central range and the share it holds; pass it straight to convert_range_to_distribution."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
},
"DistributionSupport": {
"type": "object",
"title": "DistributionSupport",
"required": [
"min",
"max"
],
"properties": {
"max": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Max"
},
"min": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Min"
}
},
"description": "The lowest and highest possible values; null where unbounded."
},
"ThresholdProbabilities": {
"type": "object",
"title": "ThresholdProbabilities",
"required": [
"value",
"p_below",
"p_above"
],
"properties": {
"value": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Value"
},
"p_above": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "P Above"
},
"p_below": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "P Below"
}
},
"description": "value, the chance of being below it (at or below for continuous types), and the chance of being above it."
}
},
"title": "ConvertDistributionToRangeResult",
"required": [
"distribution_type",
"distribution_params",
"mean",
"median",
"std",
"mode",
"quantiles",
"interval",
"threshold",
"support"
],
"properties": {
"std": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Std"
},
"mean": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Mean"
},
"mode": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Mode"
},
"notes": {
"type": "array",
"items": {
"type": "string"
},
"title": "Notes",
"description": "Explanations, for example why a value is null, or the chance of landing exactly on the threshold for whole-number distributions."
},
"median": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Median"
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"support": {
"$ref": "#/$defs/DistributionSupport"
},
"interval": {
"anyOf": [
{
"$ref": "#/$defs/RangeInterval"
},
{
"type": "null"
}
],
"description": "The range holding the chosen share of outcomes, in the input shape convert_range_to_distribution accepts. Null where a range does not apply."
},
"quantiles": {
"type": "object",
"title": "Quantiles",
"description": "Requested percentiles, keyed p5, p50 and so on.",
"additionalProperties": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
]
}
},
"threshold": {
"anyOf": [
{
"$ref": "#/$defs/ThresholdProbabilities"
},
{
"type": "null"
}
],
"description": "Chances of landing below and above the threshold. Null when no threshold was given."
},
"distribution_type": {
"type": "string",
"title": "Distribution Type"
},
"distribution_params": {
"type": "object",
"title": "Distribution Params",
"additionalProperties": true
}
},
"description": "A distribution in plain numbers. Values that do not apply are null, and notes explains why. The reverse of convert_range_to_distribution."
},
"annotations": {
"title": "Turn distribution parameters into a min–max range",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}| boolean |
| true to also return a histogram (trial counts per value bin) for up to 3 of the rows. |
| period_to | any | Instead of periods: the last index of a range (inclusive). |
| threshold | any | A value to test: returns, for each node and period, the chance (0 to 1) that it is at least this value (or at most it, see threshold_direction), for example the chance cash is at least 0 in month 6. |
| percentiles | any | Percentiles to return, as fractions from 0 to 1 (0.95 is the 95th percentile). Default [0.1, 0.5, 0.9]. |
| period_from | any | Instead of periods: the first index of a range of periods. |
| wait_seconds | number | If the run is still going, wait up to this many seconds (0 to 50, default 30) for it to finish before answering. Returns as soon as it finishes. 0 answers at once with the current percent done. |
| threshold_direction | string | at_least (default): the chance of being greater than or equal to threshold. at_most: the chance of being less than or equal to it. |
{
"name": "get_simulation_results",
"title": "Get the results of a simulation you already ran",
"description": "Checks on, and reads, a run you started with run_monte_carlo_simulation, rank_inputs_by_impact or summarize_outcome_scenarios, using its run_id. Use this when a run tool returned status running or queued: it waits up to 30 seconds for the run to finish, then returns its status and percent done, or the finished result, so call it again until status is completed. Use it also to get specific numbers from a finished simulation without running it again (a finished run keeps every node's and edge's statistics for every period): pass nodes (node, edge or metric ids), periods, percentiles such as 0.05 or 0.95, a threshold to get the chance a value is at least or at most some number, or histogram for the distribution's shape. Without those it returns the summary (or the ranking, or the scenarios). A failed run returns its error and is not charged. Only the caller who started the run can read it, and only with the run_id, which is returned to that caller alone. A run started without an account can be read for 24 hours and only from the same network address and client, because a caller without an account is recognized by them; sign in with a free Kromatic account for runs that are not tied to one connection. Credentials go in the Authorization header as a Bearer credential; no Neumann tool takes an api_key argument. Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.",
"inputSchema": {
"type": "object",
"title": "GetSimulationResultsInput",
"required": [
"run_id"
],
"properties": {
"nodes": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Nodes",
"default": null,
"examples": [
[
"revenue",
"npv"
]
],
"description": "Ids of the nodes, edges or metrics (output_request.aggregations ids) to return numbers for. Default: the output nodes."
},
"run_id": {
"type": "string",
"title": "Run Id",
"description": "The run_id returned by run_monte_carlo_simulation, rank_inputs_by_impact or summarize_outcome_scenarios."
},
"periods": {
"anyOf": [
{
"type": "array",
"items": {
"type": "integer"
}
},
{
"type": "null"
}
],
"title": "Periods",
"default": null,
"examples": [
[
0,
5,
11
]
],
"description": "Time period indices to return, counting from 0. Default: the last period only. Ignored for metrics, which cover the whole run."
},
"histogram": {
"type": "boolean",
"title": "Histogram",
"default": false,
"description": "true to also return a histogram (trial counts per value bin) for up to 3 of the rows."
},
"period_to": {
"anyOf": [
{
"type": "integer",
"minimum": 0
},
{
"type": "null"
}
],
"title": "Period To",
"default": null,
"description": "Instead of periods: the last index of a range (inclusive)."
},
"threshold": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Threshold",
"default": null,
"examples": [
0
],
"description": "A value to test: returns, for each node and period, the chance (0 to 1) that it is at least this value (or at most it, see threshold_direction), for example the chance cash is at least 0 in month 6."
},
"percentiles": {
"anyOf": [
{
"type": "array",
"items": {
"type": "number",
"maximum": 1,
"minimum": 0
},
"maxItems": 20
},
{
"type": "null"
}
],
"title": "Percentiles",
"default": null,
"examples": [
[
0.05,
0.5,
0.95
]
],
"description": "Percentiles to return, as fractions from 0 to 1 (0.95 is the 95th percentile). Default [0.1, 0.5, 0.9]."
},
"period_from": {
"anyOf": [
{
"type": "integer",
"minimum": 0
},
{
"type": "null"
}
],
"title": "Period From",
"default": null,
"description": "Instead of periods: the first index of a range of periods."
},
"wait_seconds": {
"type": "number",
"title": "Wait Seconds",
"default": 30,
"maximum": 50,
"minimum": 0,
"description": "If the run is still going, wait up to this many seconds (0 to 50, default 30) for it to finish before answering. Returns as soon as it finishes. 0 answers at once with the current percent done."
},
"threshold_direction": {
"enum": [
"at_least",
"at_most"
],
"type": "string",
"title": "Threshold Direction",
"default": "at_least",
"description": "at_least (default): the chance of being greater than or equal to threshold. at_most: the chance of being less than or equal to it."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"QueryRow": {
"type": "object",
"title": "QueryRow",
"required": [
"id",
"period",
"mean",
"std",
"min",
"max",
"percentiles"
],
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"max": {
"type": "number",
"title": "Max"
},
"min": {
"type": "number",
"title": "Min"
},
"std": {
"type": "number",
"title": "Std"
},
"mean": {
"type": "number",
"title": "Mean"
},
"period": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Period",
"description": "Period index from 0; null for a metric."
},
"histogram": {
"anyOf": [
{
"$ref": "#/$defs/QueryHistogram"
},
{
"type": "null"
}
],
"default": null
},
"percentiles": {
"type": "object",
"title": "Percentiles",
"description": "Keyed like 'p10', 'p50', 'p95' (or 'p2.5'), from your percentiles.",
"additionalProperties": {
"type": "number"
}
},
"probability": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Probability",
"default": null,
"description": "The chance of meeting the threshold, if you gave one."
}
},
"description": "One node (or edge, or metric) in one period."
},
"RunSummary": {
"type": "object",
"title": "RunSummary",
"required": [
"trials",
"time_periods"
],
"properties": {
"note": {
"type": "string",
"title": "Note",
"default": "This is a summary. For other nodes, periods, percentiles, the chance of reaching a threshold, or a histogram, call get_simulation_results with this run_id and the nodes, periods, percentiles, threshold or histogram arguments."
},
"trials": {
"type": "integer",
"title": "Trials"
},
"metrics": {
"type": "array",
"items": {
"$ref": "#/$defs/MetricSummary"
},
"title": "Metrics"
},
"outputs": {
"type": "array",
"items": {
"$ref": "#/$defs/OutputNodeSummary"
},
"title": "Outputs"
},
"other_nodes": {
"type": "array",
"items": {
"type": "string"
},
"title": "Other Nodes",
"description": "Ids of the other nodes, which you can query by name."
},
"time_periods": {
"type": "integer",
"title": "Time Periods"
},
"other_nodes_count": {
"type": "integer",
"title": "Other Nodes Count",
"default": 0,
"description": "How many other nodes there are."
}
},
"description": "The headline numbers of a finished simulation."
},
"TornadoRow": {
"type": "object",
"title": "TornadoRow",
"required": [
"rank",
"input_id",
"baseline_input",
"low_input",
"high_input",
"outcome_at_low",
"outcome_at_high",
"swing",
"elasticity"
],
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name",
"default": null
},
"rank": {
"type": "integer",
"title": "Rank",
"description": "1 = the input with the biggest impact."
},
"swing": {
"type": "number",
"title": "Swing",
"description": "abs(outcome_at_high - outcome_at_low): the bar's length."
},
"input_id": {
"type": "string",
"title": "Input Id"
},
"low_input": {
"type": "number",
"title": "Low Input",
"description": "The input at the lowest percentile tried."
},
"elasticity": {
"type": "number",
"title": "Elasticity",
"description": "Roughly the % change in the outcome per 1% change in the input (unsigned)."
},
"high_input": {
"type": "number",
"title": "High Input",
"description": "The input at the highest percentile tried."
},
"baseline_input": {
"type": "number",
"title": "Baseline Input",
"description": "The input's median, where it is held otherwise."
},
"outcome_at_low": {
"type": "number",
"title": "Outcome At Low",
"description": "The outcome's mean with the input at low_input."
},
"outcome_at_high": {
"type": "number",
"title": "Outcome At High",
"description": "The outcome's mean with the input at high_input."
}
},
"description": "One input's bar in the tornado chart."
},
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"QueryResult": {
"type": "object",
"title": "QueryResult",
"properties": {
"note": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Note",
"default": null
},
"rows": {
"type": "array",
"items": {
"$ref": "#/$defs/QueryRow"
},
"title": "Rows"
},
"truncated": {
"type": "boolean",
"title": "Truncated",
"default": false
},
"unknown_ids": {
"type": "array",
"items": {
"type": "string"
},
"title": "Unknown Ids"
}
},
"description": "Specific numbers you asked for from a finished run."
},
"RunProgress": {
"type": "object",
"title": "RunProgress",
"required": [
"percent",
"done",
"total",
"unit"
],
"properties": {
"done": {
"type": "integer",
"title": "Done"
},
"unit": {
"enum": [
"trials",
"runs"
],
"type": "string",
"title": "Unit",
"description": "trials for a simulation; runs (internal simulations) for a sensitivity sweep."
},
"total": {
"type": "integer",
"title": "Total"
},
"percent": {
"type": "number",
"title": "Percent",
"description": "0 to 100."
}
},
"description": "How far a queued or running run has got."
},
"DrivingInput": {
"type": "object",
"title": "DrivingInput",
"required": [
"node_id",
"value"
],
"properties": {
"value": {
"type": "number",
"title": "Value",
"description": "The root node's own distribution value at the scenario percentile (best-effort marginal driver; exact for monotone single-input graphs)."
},
"node_id": {
"type": "string",
"title": "Node Id"
}
},
"description": "A best-effort driving input value for a scenario."
},
"OutputSeries": {
"type": "object",
"title": "OutputSeries",
"required": [
"periods",
"mean",
"p10",
"p50",
"p90"
],
"properties": {
"p10": {
"type": "array",
"items": {
"type": "number"
},
"title": "P10"
},
"p50": {
"type": "array",
"items": {
"type": "number"
},
"title": "P50"
},
"p90": {
"type": "array",
"items": {
"type": "number"
},
"title": "P90"
},
"mean": {
"type": "array",
"items": {
"type": "number"
},
"title": "Mean"
},
"periods": {
"type": "array",
"items": {
"type": "integer"
},
"title": "Periods",
"description": "Period indices, counted from 0."
}
},
"description": "An output node over time, sampled to at most 24 periods."
},
"ScenarioCase": {
"type": "object",
"title": "ScenarioCase",
"required": [
"label",
"percentile",
"output_value"
],
"properties": {
"label": {
"type": "string",
"title": "Label",
"description": "'worst' | 'median' | 'best' | 'p<N>'."
},
"percentile": {
"type": "number",
"title": "Percentile"
},
"output_value": {
"type": "number",
"title": "Output Value",
"description": "The target node's value at this percentile of its distribution."
},
"driving_inputs": {
"type": "array",
"items": {
"$ref": "#/$defs/DrivingInput"
},
"title": "Driving Inputs"
}
},
"description": "One scenario: the target's outcome at a percentile + its driving inputs."
},
"MetricSummary": {
"type": "object",
"title": "MetricSummary",
"required": [
"id",
"mean",
"p10",
"p50",
"p90"
],
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"p10": {
"type": "number",
"title": "P10"
},
"p50": {
"type": "number",
"title": "P50"
},
"p90": {
"type": "number",
"title": "P90"
},
"mean": {
"type": "number",
"title": "Mean"
},
"target": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Target",
"default": null,
"description": "The node or metric it was computed on."
},
"function": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Function",
"default": null
},
"probability": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Probability",
"default": null,
"description": "For a prob metric: the probability (0 to 1), which is its mean."
}
},
"description": "One requested metric (npv, irr, payback, prob, ...) across trials."
},
"QueryHistogram": {
"type": "object",
"title": "QueryHistogram",
"required": [
"counts",
"bins"
],
"properties": {
"bins": {
"type": "array",
"items": {
"type": "number"
},
"title": "Bins"
},
"counts": {
"type": "array",
"items": {
"type": "integer"
},
"title": "Counts"
}
},
"description": "Trial counts per bin; ``bins`` has one more edge than ``counts``."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
},
"OutputNodeSummary": {
"type": "object",
"title": "OutputNodeSummary",
"required": [
"node_id",
"period",
"mean",
"p10",
"p50",
"p90",
"min",
"max"
],
"properties": {
"max": {
"type": "number",
"title": "Max"
},
"min": {
"type": "number",
"title": "Min"
},
"p10": {
"type": "number",
"title": "P10"
},
"p50": {
"type": "number",
"title": "P50"
},
"p90": {
"type": "number",
"title": "P90"
},
"mean": {
"type": "number",
"title": "Mean"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Name",
"default": null
},
"period": {
"type": "integer",
"title": "Period",
"description": "The period these numbers describe (the last one)."
},
"series": {
"anyOf": [
{
"$ref": "#/$defs/OutputSeries"
},
{
"type": "null"
}
],
"default": null,
"description": "Mean and P10/P50/P90 per period. Absent for a one-period model."
},
"node_id": {
"type": "string",
"title": "Node Id"
}
},
"description": "One output node: its final period, plus a compact series over time."
}
},
"title": "GetSimulationResultsResult",
"required": [
"run_id",
"status",
"tier",
"total_trials",
"trials_completed",
"created_at"
],
"properties": {
"kind": {
"enum": [
"simulation",
"sensitivity",
"scenarios"
],
"type": "string",
"title": "Kind",
"default": "simulation"
},
"tier": {
"type": "string",
"title": "Tier"
},
"error": {
"anyOf": [
{
"type": "object",
"additionalProperties": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Error",
"default": null,
"description": "Error code and message if the run failed; otherwise null."
},
"model": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Model",
"default": null,
"description": "The graph this run used, for the owner only (neumann#395). Present once the run has stored one: an anonymous run's model directly, or an account run's auto-saved graph content."
},
"query": {
"anyOf": [
{
"$ref": "#/$defs/QueryResult"
},
{
"type": "null"
}
],
"default": null
},
"run_id": {
"type": "string",
"title": "Run Id"
},
"status": {
"type": "string",
"title": "Status",
"description": "The run's status, for example completed or failed."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"summary": {
"anyOf": [
{
"$ref": "#/$defs/RunSummary"
},
{
"type": "null"
}
],
"default": null,
"description": "Per-node and per-edge statistics for each period (mean, standard deviation, minimum, maximum, percentiles, histogram) plus requested financial metrics. Null until available. Its layout differs from run_monte_carlo_simulation's result."
},
"tornado": {
"anyOf": [
{
"type": "array",
"items": {
"$ref": "#/$defs/TornadoRow"
}
},
{
"type": "null"
}
],
"title": "Tornado",
"default": null
},
"progress": {
"anyOf": [
{
"$ref": "#/$defs/RunProgress"
},
{
"type": "null"
}
],
"default": null
},
"next_step": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Next Step",
"default": null
},
"scenarios": {
"anyOf": [
{
"type": "array",
"items": {
"$ref": "#/$defs/ScenarioCase"
}
},
{
"type": "null"
}
],
"title": "Scenarios",
"default": null
},
"created_at": {
"type": "string",
"title": "Created At",
"description": "When the run started, as an ISO-8601 time."
},
"total_trials": {
"type": "integer",
"title": "Total Trials"
},
"credits_debited": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credits Debited",
"default": null
},
"baseline_outcome": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Baseline Outcome",
"default": null
},
"trials_completed": {
"type": "integer",
"title": "Trials Completed"
},
"estimated_seconds_remaining": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Estimated Seconds Remaining",
"default": null
}
},
"description": "Status and summary of an earlier run."
},
"annotations": {
"title": "Get the results of a simulation you already ran",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}| expected | any | What you expected to happen instead. |
| tool_name | any | The Neumann tool the report is about, for example run_monte_carlo_simulation. |
| user_goal | any | What the user was trying to do, as a general task in a few words, for example "estimate a project budget". No names, company names or figures. |
| error_text | any | The error code and message the tool returned, if any. Remove any personal data or user figures it quotes. |
| suggestion | any | What would have helped: a fix, a new feature or clearer wording. |
| sender_name | any | Optional name, up to 200 characters. |
| sender_email | any | Optional. The user's email address, only if they want a reply and gave it to you. Do not invent one. No copy is sent to it. |
| feedback_type | string | What kind of report this is. bug: a tool errored or broke. wrong_result: it ran but the numbers look wrong. unmet_use_case: the user needed something no tool does. feature_request: a missing option or parameter. confusing: a description, output or error was hard to understand. praise: something work… |
| what_happened | any | What actually happened, in general terms, without the user's numbers. |
{
"name": "send_feedback",
"title": "Send feedback or a bug report to the Neumann team",
"description": "Sends a short report about Neumann to the team that builds it. Use this when the user wants to report a problem, a wrong result, a confusing message or a missing feature (including asking you to pass a request or suggestion on to the team), or has agreed to your offer to send one. Send only after the user agrees: when a tool fails, first tell the user what happened and ask, and do not call this tool until they say yes. Good moments to offer: a tool returned an error or a result that looks wrong, the user needed something Neumann could not do, or the work with Neumann is wrapping up and the user might want to say what worked. Offer it as a question, for example: 'Want me to send Neumann's team a short note about this?' The team reads every report. Do not offer after each routine successful call. Put several points in one report: a signed-in account may send 5 per hour and 20 per day, and callers without an account share 60 per hour and 300 per day. Only message is required. Fill in the other fields that apply so the team can act without guessing. Write in your own words. Never include personal data (names, email addresses, company names), the user's own numbers (inputs or results), secrets or keys, or the conversation transcript; describe the task and any wrong result in general terms instead. Add sender_email only if the user wants a reply. If you are signed in, your account id is included. No account is needed. It returns status \"sent\". Cost: free, with or without an account -- it debits no credits and spends none of your free daily runs.",
"inputSchema": {
"type": "object",
"title": "SendFeedbackInput",
"required": [
"message"
],
"properties": {
"impact": {
"anyOf": [
{
"enum": [
"blocked",
"workaround",
"minor",
"none"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Impact",
"default": null,
"description": "How much it cost the user. blocked: could not finish. workaround: finished another way. minor: an annoyance. none: no cost, for example praise."
},
"run_id": {
"anyOf": [
{
"type": "string",
"maxLength": 100
},
{
"type": "null"
}
],
"title": "Run Id",
"default": null,
"description": "The run_id the report is about, if a run was involved."
},
"message": {
"type": "string",
"title": "Message",
"examples": [
"rank_inputs_by_impact returned an empty list for a model with two inputs, so I could not tell the user which one mattered more."
],
"maxLength": 5000,
"minLength": 10,
"description": "The report, in your own words, 10 to 5,000 characters. Say what you tried, what happened and what you expected. Leave out names, companies, the user's numbers (inputs or results) and the conversation itself: write \"a revenue forecast\", not its figures."
},
"expected": {
"anyOf": [
{
"type": "string",
"maxLength": 2000
},
{
"type": "null"
}
],
"title": "Expected",
"default": null,
"description": "What you expected to happen instead."
},
"tool_name": {
"anyOf": [
{
"type": "string",
"maxLength": 100
},
{
"type": "null"
}
],
"title": "Tool Name",
"default": null,
"description": "The Neumann tool the report is about, for example run_monte_carlo_simulation."
},
"user_goal": {
"anyOf": [
{
"type": "string",
"maxLength": 500
},
{
"type": "null"
}
],
"title": "User Goal",
"default": null,
"description": "What the user was trying to do, as a general task in a few words, for example \"estimate a project budget\". No names, company names or figures."
},
"error_text": {
"anyOf": [
{
"type": "string",
"maxLength": 2000
},
{
"type": "null"
}
],
"title": "Error Text",
"default": null,
"description": "The error code and message the tool returned, if any. Remove any personal data or user figures it quotes."
},
"suggestion": {
"anyOf": [
{
"type": "string",
"maxLength": 2000
},
{
"type": "null"
}
],
"title": "Suggestion",
"default": null,
"description": "What would have helped: a fix, a new feature or clearer wording."
},
"sender_name": {
"anyOf": [
{
"type": "string",
"maxLength": 200
},
{
"type": "null"
}
],
"title": "Sender Name",
"default": null,
"description": "Optional name, up to 200 characters."
},
"sender_email": {
"anyOf": [
{
"type": "string",
"format": "email"
},
{
"type": "null"
}
],
"title": "Sender Email",
"default": null,
"description": "Optional. The user's email address, only if they want a reply and gave it to you. Do not invent one. No copy is sent to it."
},
"feedback_type": {
"enum": [
"bug",
"unmet_use_case",
"feature_request",
"confusing",
"wrong_result",
"praise",
"other"
],
"type": "string",
"title": "Feedback Type",
"default": "other",
"description": "What kind of report this is. bug: a tool errored or broke. wrong_result: it ran but the numbers look wrong. unmet_use_case: the user needed something no tool does. feature_request: a missing option or parameter. confusing: a description, output or error was hard to understand. praise: something worked well. other: anything else (the default)."
},
"what_happened": {
"anyOf": [
{
"type": "string",
"maxLength": 2000
},
{
"type": "null"
}
],
"title": "What Happened",
"default": null,
"description": "What actually happened, in general terms, without the user's numbers."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "SendFeedbackResult",
"required": [
"status",
"message"
],
"properties": {
"status": {
"type": "string",
"title": "Status",
"description": "sent on success."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"message": {
"type": "string",
"title": "Message",
"description": "Confirmation text, including whether the team can reply."
}
},
"description": "Confirmation that the report was sent."
},
"annotations": {
"title": "Send feedback or a bug report to the Neumann team",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}| The run to share, as returned by any run tool. For a run made without an account, sign in and then call again with this same run_id: signing in alone shares nothing. |
{
"name": "create_result_share_link",
"title": "Create a public link to a result",
"description": "Creates a public web link to one of your results, so you can hand the numbers to someone who has no Neumann account. Use this when the user wants to send, publish or show a result to another person; to put the numbers in the conversation instead, call get_simulation_results. It works for any run you own: a run from run_monte_carlo_simulation, rank_inputs_by_impact or summarize_outcome_scenarios, and a run of a graph you saved. There is one share tool for every kind of run -- do not look for a separate one. Pass the run_id the run tool returned when the run was made, earlier in the conversation; no tool lists runs, and you do not need a graph_id. That holds for a run of a saved model too: when the user asks to share the run of a saved graph, call this tool directly with that run's run_id -- list_graphs and get_graph return graph_ids, not run_ids, so they are not a step here. Calling it again for the same run returns the same link rather than a second one. Anyone who has the link can open the result without signing in, so ask the user before you create one. delete_run deletes the stored result, which also stops its share link working. There is no way to turn off a link and keep the result. A run made without an account takes two calls, and the run_id is what carries it from one to the other. First call: the caller has no account, so call this tool with the run_id anyway; nothing is shared, and it returns a message asking the user to sign in with a free Kromatic account -- tell the user that. Second call: once the user has signed in, call this tool again with the SAME run_id. Only that second call shares the run and keeps it on the account; signing in alone shares nothing, and a different run_id, or a new run, does not carry the claim. Do it within 24 hours, because a run made without an account is deleted after that. When you tell the user what happens next, say both steps: sign in, then you will share it using the same run. It returns the share_url. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.",
"inputSchema": {
"type": "object",
"title": "CreateResultShareLinkInput",
"required": [
"run_id"
],
"properties": {
"run_id": {
"type": "string",
"title": "Run Id",
"examples": [
"run_8f3c2a"
],
"description": "The run to share, as returned by any run tool. For a run made without an account, sign in and then call again with this same run_id: signing in alone shares nothing."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "CreateResultShareLinkResult",
"required": [
"share_url"
],
"properties": {
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"share_url": {
"type": "string",
"title": "Share Url",
"description": "A web address anyone can open to see this result, with no Neumann account and no credential. Asking again for the same run returns this same link."
}
},
"description": "The public link to the result."
},
"annotations": {
"title": "Create a public link to a result",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}| object |
| The model to save: its uncertain inputs (root_nodes), the formulas over them (calc_nodes), the links between them (edges) and the run settings (run_params). The same shape run_monte_carlo_simulation takes, except that an input may be saved before it has a distribution: give it distribution_type null… |
| graph_id | any | Omit to save a new graph. Give the graph_id of a graph you saved before to replace that same graph with this version, keeping its earlier versions. |
{
"name": "save_graph",
"title": "Save a model to your account",
"description": "Saves a model to your Neumann account so you can come back to it instead of describing it again. A saved model is called a graph: its uncertain inputs, the formulas that combine them, and the links between them. Use this when the user will revisit this model -- a budget, a plan, a business case they will update -- or when you want to re-analyse it later without resending it; for a one-off question, pass the model inline to run_monte_carlo_simulation and save nothing. Omit graph_id to save a new graph. Pass the graph_id of a graph you saved before to replace that same graph with this version; the earlier versions are kept, so replacing is not losing anything. An input may be saved before it has a distribution, so you can build a draft model over a conversation; a graph with such an input cannot be run or analysed until each input has one. An input can also be given as an estimated range (estimate: worst, best, most likely) with a distribution_type and no params: the save fits the params to the range. Changing a saved input's range re-fits its params, and changing only its params works the range out again. If a range cannot be fitted, the error estimate_fit_failed names the input and nothing at all is saved: not that input, not the rest of the model, and a graph you were replacing keeps its last saved version. So after that error there is nothing new to read back with get_graph; tell the user which range could not be fitted and fix it. It returns the graph_id to use later, the version_id of the version it just stored, the name, and when it was last updated. Use that graph_id with get_graph to read the model back, with rank_inputs_by_impact or summarize_outcome_scenarios in place of an inline graph, and with delete_graph to remove it. run_monte_carlo_simulation does not take a graph_id: read the graph with get_graph and pass it inline. It needs a Neumann account: send your key, or your signed-in token, in the Authorization header as a Bearer credential. No Neumann tool takes an api_key argument. Cost: free -- it debits no credits and spends none of your free daily runs -- but it needs an account; an anonymous caller gets authentication_required.",
"inputSchema": {
"type": "object",
"title": "SaveGraphInput",
"required": [
"graph",
"name"
],
"properties": {
"name": {
"type": "string",
"title": "Name",
"examples": [
"Q3 launch budget"
],
"maxLength": 255,
"minLength": 1,
"description": "A short name the user will recognise later, shown by list_graphs. Use the user's own words for the thing being modelled."
},
"graph": {
"type": "object",
"examples": [
{
"edges": [
{
"id": "e1",
"source": "customers",
"target": "revenue"
},
{
"id": "e2",
"source": "price",
"target": "revenue"
}
],
"calc_nodes": [
{
"id": "revenue",
"name": "Monthly revenue",
"formula": "{e1} * {e2}"
}
],
"root_nodes": [
{
"id": "customers",
"name": "Customers per month",
"distribution_type": "normal",
"distribution_params": {
"std": 200,
"mean": 1000
}
},
{
"id": "price",
"name": "Price (USD)",
"distribution_type": "triangle",
"distribution_params": {
"max_val": 15,
"min_val": 8,
"mode_val": 10
}
}
],
"run_params": {
"trials": 1000,
"time_periods": 12
}
}
],
"description": "The model to save: its uncertain inputs (root_nodes), the formulas over them (calc_nodes), the links between them (edges) and the run settings (run_params). The same shape run_monte_carlo_simulation takes, except that an input may be saved before it has a distribution: give it distribution_type null and distribution_params {}. A graph with such an input cannot be run until you give it one. An input may also carry an estimate, the range behind it (worst, best, mode): send a range and a distribution_type without params and the params are fitted to the range on save; send only params and the range they imply is stored. Leave estimate out to keep the one already saved. Only this outline is published here: the full schema is on run_monte_carlo_simulation's graph parameter, and the neumann://catalog resource lists every distribution and formula function. Neumann checks the model against that full schema when you call this tool and names any problem."
},
"graph_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Graph Id",
"default": null,
"examples": [
"8f3c2a"
],
"description": "Omit to save a new graph. Give the graph_id of a graph you saved before to replace that same graph with this version, keeping its earlier versions."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"BillingInfo": {
"type": "object",
"title": "BillingInfo",
"required": [
"principal",
"auth_source",
"charged_to"
],
"properties": {
"principal": {
"enum": [
"anonymous",
"account"
],
"type": "string",
"title": "Principal",
"description": "account when an API key or signed-in connection was recognized, otherwise anonymous."
},
"account_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Id",
"default": null,
"description": "Your account id, or null without an account."
},
"charged_to": {
"enum": [
"anonymous_allowance",
"free_daily_run",
"credits",
"none"
],
"type": "string",
"title": "Charged To",
"description": "What paid for this call: anonymous_allowance (one of the free daily runs for callers without an account), free_daily_run (one of a signed-in account's free daily runs), credits (the account's credit balance), or none (the call is free)."
},
"auth_source": {
"enum": [
"bearer",
"anonymous"
],
"type": "string",
"title": "Auth Source",
"description": "How you were identified: bearer (a credential sent in the Authorization: Bearer header) or anonymous."
},
"account_status": {
"anyOf": [
{
"enum": [
"matched",
"created"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Status",
"default": null,
"description": "matched for an existing account, created when this call created one on first sign-in. Null without an account."
},
"credit_balance": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Credit Balance",
"default": null,
"description": "Your credit balance after this call. Null without an account."
},
"credits_debited": {
"type": "integer",
"title": "Credits Debited",
"default": 0,
"description": "Credits this call used (0 when free)."
},
"free_run_limits": {
"anyOf": [
{
"$ref": "#/$defs/SignedInLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The size a run must be within to use one of this account's free daily runs. Null unless the account signed in with Kromatic."
},
"anonymous_limits": {
"anyOf": [
{
"$ref": "#/$defs/AnonymousLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "The no-account limits. Null with an account."
},
"free_runs_reset_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Free Runs Reset At",
"default": null,
"description": "When this account's free daily runs refill (the next UTC midnight), as an ISO-8601 time. Null unless the account signed in with Kromatic."
},
"free_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Free Runs Remaining Today",
"default": null,
"description": "Free runs left today on this account, after this call. Null unless the account signed in with Kromatic: an account created with POST https://neumann.kromatic.com/api/v1/accounts has no free daily runs."
},
"anonymous_allowance_resets_at": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Anonymous Allowance Resets At",
"default": null,
"description": "When free runs refill (next UTC midnight), as an ISO-8601 time. Null with an account."
},
"anonymous_runs_remaining_today": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Anonymous Runs Remaining Today",
"default": null,
"description": "Free runs left today for a caller without an account, after this call. Null with an account -- see free_runs_remaining_today instead."
}
},
"description": "Who you are and what this call cost. Present on every result. charged_to says what paid; credits_debited and anonymous_runs_remaining_today say how much."
},
"SignedInLimits": {
"type": "object",
"title": "SignedInLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Maximum nodes in a free run's graph."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Maximum trials in a free run."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC calendar day."
}
},
"description": "The free signed-in tier's bounds (neumann#334), rendered from ``Settings``."
},
"AnonymousLimits": {
"type": "object",
"title": "AnonymousLimits",
"required": [
"runs_per_day",
"max_trials",
"max_nodes"
],
"properties": {
"max_nodes": {
"type": "integer",
"title": "Max Nodes",
"description": "Most nodes (inputs plus formula nodes) allowed without an account."
},
"max_trials": {
"type": "integer",
"title": "Max Trials",
"description": "Most trials allowed in one run without an account."
},
"runs_per_day": {
"type": "integer",
"title": "Runs Per Day",
"description": "Free runs per UTC day."
}
},
"description": "The limits that apply without an account."
}
},
"title": "SaveGraphResult",
"required": [
"graph_id",
"version_id",
"name",
"updated_at"
],
"properties": {
"name": {
"type": "string",
"title": "Name",
"description": "The name this graph is saved under."
},
"billing": {
"anyOf": [
{
"$ref": "#/$defs/BillingInfo"
},
{
"type": "null"
}
],
"default": null,
"description": "Who you are and what this call cost: principal, auth source, credits debited and balance, or the anonymous allowance left today."
},
"graph_id": {
"type": "string",
"title": "Graph Id",
"description": "The id of the saved graph. Pass it to get_graph, to rank_inputs_by_impact or summarize_outcome_scenarios in place of an inline graph, or to delete_graph."
},
"updated_at": {
"type": "string",
"title": "Updated At",
"description": "When this graph was last saved, as an ISO-8601 time."
},
"version_id": {
"type": "string",
"title": "Version Id",
"description": "The id of the version just stored. Earlier versions are kept."
}
},
"description": "What was saved."
},
"annotations": {
"title": "Save a model to your account",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}