Power Automate MCP Server by FlowStudio is an MCP server published by io.github.ninihen1, hosted at mcp.flowstudio.app. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 27 tools, including tool_search, list_skills, report_bug, get_task, get_live_flow_runs.
40+ tools to debug, build and monitor Power Automate flows and Power Apps canvas apps (Preview)
Nothing else in the archive shares these values.
Find a tool listed here instead of guessing its name, and get its definition. Query forms: (1) "skill:<name>" — a whole bundle; call list_skills for the names; (2) "select:name1,name2" — exact tools; (3) free text like "cancel run" — ranked against name and description. Non-billable.
| Parameter | Type | Description |
|---|---|---|
| query * | string | Search query. Forms: "select:name1,name2", "skill:<name>", or free-text keywords. |
| max_results | integer | Max tools to return for keyword queries (default 5). Ignored for select: and skill: queries. |
{
"name": "tool_search",
"title": "Search tools",
"description": "Find a tool listed here instead of guessing its name, and get its definition. Query forms: (1) \"skill:<name>\" — a whole bundle; call list_skills for the names; (2) \"select:name1,name2\" — exact tools; (3) free text like \"cancel run\" — ranked against name and description. Non-billable.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Search query. Forms: \"select:name1,name2\", \"skill:<name>\", or free-text keywords."
},
"max_results": {
"type": "integer",
"default": 5,
"description": "Max tools to return for keyword queries (default 5). Ignored for select: and skill: queries."
}
}
},
"annotations": {
"title": "Search tools",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}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.
Skill bundles: groups of the tools listed here that are used together for one task (diagnose-connection-references, build-flow, debug-flow, monitor-flow, discover, governance). Returns each bundle's name and one-line description. Use it when unsure which tools fit a request; tool_search "skill:<name>" returns the bundle's full guidance and definitions. Non-billable.
No parameters.
{
"name": "list_skills",
"title": "List skill bundles",
"description": "Skill bundles: groups of the tools listed here that are used together for one task (diagnose-connection-references, build-flow, debug-flow, monitor-flow, discover, governance). Returns each bundle's name and one-line description. Use it when unsure which tools fit a request; tool_search \"skill:<name>\" returns the bundle's full guidance and definitions. Non-billable.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "List skill bundles",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Report a Flow Studio MCP bug or missing capability, append text evidence, or check your reports. Free and available even after quota is reached. Do not include passwords, access tokens, secrets, or full flow definitions unless necessary.
| Parameter | Type | Description |
|---|---|---|
| chunk | integer | Optional. Omit to append the next chunk automatically. |
| action * | string | one of ["report","append","status","list"] |
| notify | boolean | |
| ticket | string | |
| content | string | Text attachment body. Max 64 KB per call. |
| details | string | |
| summary | string | |
| category | string | one of ["wrong-result","error","missing-capability","docs-or-hints","performance","other"] |
| severity | string | one of ["blocker","major","minor"] |
| file_name | string | |
| flow_name | string | |
| tool_name | string | |
| final_chunk | boolean | |
| content_type | string | Media type of the attachment. text/plain (default), text/csv, text/markdown, application/json, application/har+json, application/xml, image/png, image/jpeg, image/gif, image/webp, application/pdf. |
| contact_email | string | |
| content_base64 | string | Binary attachment body, base64-encoded. Max 256 KB decoded per call. Use for images/PDF; pass text through `content` instead. Do not send both. |
| environment_name | string | |
| include_diagnostics | boolean |
{
"name": "report_bug",
"title": "Report a bug",
"description": "Report a Flow Studio MCP bug or missing capability, append text evidence, or check your reports. Free and available even after quota is reached. Do not include passwords, access tokens, secrets, or full flow definitions unless necessary.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"chunk": {
"type": "integer",
"minimum": 0,
"description": "Optional. Omit to append the next chunk automatically."
},
"action": {
"enum": [
"report",
"append",
"status",
"list"
],
"type": "string"
},
"notify": {
"type": "boolean",
"default": true
},
"ticket": {
"type": "string"
},
"content": {
"type": "string",
"description": "Text attachment body. Max 64 KB per call."
},
"details": {
"type": "string",
"maxLength": 100000
},
"summary": {
"type": "string",
"maxLength": 200
},
"category": {
"enum": [
"wrong-result",
"error",
"missing-capability",
"docs-or-hints",
"performance",
"other"
],
"type": "string",
"default": "other"
},
"severity": {
"enum": [
"blocker",
"major",
"minor"
],
"type": "string",
"default": "major"
},
"file_name": {
"type": "string"
},
"flow_name": {
"type": "string"
},
"tool_name": {
"type": "string"
},
"final_chunk": {
"type": "boolean"
},
"content_type": {
"type": "string",
"description": "Media type of the attachment. text/plain (default), text/csv, text/markdown, application/json, application/har+json, application/xml, image/png, image/jpeg, image/gif, image/webp, application/pdf."
},
"contact_email": {
"type": "string"
},
"content_base64": {
"type": "string",
"description": "Binary attachment body, base64-encoded. Max 256 KB decoded per call. Use for images/PDF; pass text through `content` instead. Do not send both."
},
"environment_name": {
"type": "string"
},
"include_diagnostics": {
"type": "boolean",
"default": true
}
}
},
"annotations": {
"title": "Report a bug",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Get the status and result of a long-running tool call. When a tool replies with a taskId and status "working", the work is still running on the server: do not call that tool again. Wait pollIntervalMs, then call this with the taskId until status is completed or failed. Free.
| Parameter | Type | Description |
|---|---|---|
| taskId * | string | The taskId from the tool's reply. |
{
"name": "get_task",
"title": "Get task",
"description": "Get the status and result of a long-running tool call. When a tool replies with a taskId and status \"working\", the work is still running on the server: do not call that tool again. Wait pollIntervalMs, then call this with the taskId until status is completed or failed. Free.",
"inputSchema": {
"type": "object",
"required": [
"taskId"
],
"properties": {
"taskId": {
"type": "string",
"description": "The taskId from the tool's reply."
}
}
},
"annotations": {
"title": "Get task",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Fetch run history for a flow directly from Power Automate. Returns { runs, runCount, triggerChecks }: each run has name, status, startTime, endTime, trigger name/code, and any top-level error. IMPORTANT — no runs does NOT mean the flow is healthy. A trigger that fires and evaluates to nothing, or fails to evaluate, records a TRIGGER CHECK and never becomes a run. When there are no runs (or when includeTriggerChecks is set) this tool also reports the trigger check history, so "nothing ran" can be told apart from "the trigger has been failing". Read triggerChecks.byStatus before concluding a flow is fine.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max runs to return. Paginates automatically. Default 30. |
| status | string | Only runs with this status, e.g. Failed. |
| flowName * | string | Name (ID) of the flow. |
| startedAfter | string | ISO date-time. Only runs and checks that started at or after it. |
| startedBefore | string | ISO date-time. Only runs and checks that started before it. |
| environmentName * | string | Name of the Power Platform environment. |
| triggerCheckStatus | string | Only trigger checks with this status; reads the checks. |
| includeTriggerChecks | boolean | Also report trigger check history when runs DO exist. Checks are always reported when there are no runs. Costs two extra API calls. |
{
"name": "get_live_flow_runs",
"title": "List flow runs",
"description": "Fetch run history for a flow directly from Power Automate. Returns { runs, runCount, triggerChecks }: each run has name, status, startTime, endTime, trigger name/code, and any top-level error. IMPORTANT — no runs does NOT mean the flow is healthy. A trigger that fires and evaluates to nothing, or fails to evaluate, records a TRIGGER CHECK and never becomes a run. When there are no runs (or when includeTriggerChecks is set) this tool also reports the trigger check history, so \"nothing ran\" can be told apart from \"the trigger has been failing\". Read triggerChecks.byStatus before concluding a flow is fine.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName"
],
"properties": {
"top": {
"type": "number",
"description": "Max runs to return. Paginates automatically. Default 30."
},
"status": {
"enum": [
"Succeeded",
"Failed",
"Cancelled",
"Running"
],
"type": "string",
"description": "Only runs with this status, e.g. Failed."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"startedAfter": {
"type": "string",
"description": "ISO date-time. Only runs and checks that started at or after it."
},
"startedBefore": {
"type": "string",
"description": "ISO date-time. Only runs and checks that started before it."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
},
"triggerCheckStatus": {
"enum": [
"Succeeded",
"Failed",
"Skipped"
],
"type": "string",
"description": "Only trigger checks with this status; reads the checks."
},
"includeTriggerChecks": {
"type": "boolean",
"description": "Also report trigger check history when runs DO exist. Checks are always reported when there are no runs. Costs two extra API calls."
}
}
},
"annotations": {
"title": "List flow runs",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Fetch error details for a specific flow run from the live Power Automate API. Lists every failed action with its error code and message to help diagnose what went wrong.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max actions to return. Paginates automatically. Omit for all. |
| runName * | string | Run identifier (name field from get_live_flow_runs), or "latest" for the most recent run. |
| flowName * | string | Name (ID) of the flow. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "get_live_flow_run_error",
"title": "Get run error",
"description": "Fetch error details for a specific flow run from the live Power Automate API. Lists every failed action with its error code and message to help diagnose what went wrong.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName",
"runName"
],
"properties": {
"top": {
"type": "number",
"description": "Max actions to return. Paginates automatically. Omit for all."
},
"runName": {
"type": "string",
"description": "Run identifier (name field from get_live_flow_runs), or \"latest\" for the most recent run."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Get run error",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Read the recorded inputs and outputs of actions in one flow run. Without actionName: the top-level actions (optionally filtered by name). With actionName: every execution of that action across foreach iterations, each with repetitionIndexes, status, error, and resolved inputs/outputs. Use iterationIndex to pin one iteration; omit it for all. TRIGGER PAYLOADS: set trigger=true with a runName to get that run's trigger inputs and outputs. No Compose workaround is needed. TRIGGER CHECKS: pass checkId (from get_live_flow_runs -> triggerChecks.recent[].checkId) to read a trigger evaluation that never became a run — that is how you see WHY a trigger is failing. Do not supply runName with a checkId.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max actions or repetitions to return. Paginates automatically. Omit for all. |
| checkId | string | Trigger check id (checkId from get_live_flow_runs -> triggerChecks). Returns that check's inputs/outputs, including the failure reason. Not a run id — the two are different, which is why a check id returns WorkflowRunNotFound from the run tools. |
| runName | string | Run identifier (name field from get_live_flow_runs), or "latest" for the most recent run. Required unless checkId is given. |
| trigger | boolean | Return the RUN's trigger inputs/outputs instead of its actions. Requires runName. |
| flowName * | string | Name (ID) of the flow. |
| actionName | string | Action name. Without iterationIndex: returns all repetitions of this action across every foreach iteration. With iterationIndex: returns the single repetition matching that iteration. Omit entirely for top-level action list. |
| iterationIndex | number | Zero-based foreach iteration index. Matched against the innermost repetitionIndexes[].itemIndex in the PA repetition record. Only meaningful when actionName is also set. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "get_live_flow_run_action_outputs",
"title": "Get run action inputs and outputs",
"description": "Read the recorded inputs and outputs of actions in one flow run. Without actionName: the top-level actions (optionally filtered by name). With actionName: every execution of that action across foreach iterations, each with repetitionIndexes, status, error, and resolved inputs/outputs. Use iterationIndex to pin one iteration; omit it for all. TRIGGER PAYLOADS: set trigger=true with a runName to get that run's trigger inputs and outputs. No Compose workaround is needed. TRIGGER CHECKS: pass checkId (from get_live_flow_runs -> triggerChecks.recent[].checkId) to read a trigger evaluation that never became a run — that is how you see WHY a trigger is failing. Do not supply runName with a checkId.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName"
],
"properties": {
"top": {
"type": "number",
"description": "Max actions or repetitions to return. Paginates automatically. Omit for all."
},
"checkId": {
"type": "string",
"description": "Trigger check id (checkId from get_live_flow_runs -> triggerChecks). Returns that check's inputs/outputs, including the failure reason. Not a run id — the two are different, which is why a check id returns WorkflowRunNotFound from the run tools."
},
"runName": {
"type": "string",
"description": "Run identifier (name field from get_live_flow_runs), or \"latest\" for the most recent run. Required unless checkId is given."
},
"trigger": {
"type": "boolean",
"description": "Return the RUN's trigger inputs/outputs instead of its actions. Requires runName."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"actionName": {
"type": "string",
"description": "Action name. Without iterationIndex: returns all repetitions of this action across every foreach iteration. With iterationIndex: returns the single repetition matching that iteration. Omit entirely for top-level action list."
},
"iterationIndex": {
"type": "number",
"description": "Zero-based foreach iteration index. Matched against the innermost repetitionIndexes[].itemIndex in the PA repetition record. Only meaningful when actionName is also set."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Get run action inputs and outputs",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Run a flow on demand — the same as the maker portal's "Run flow" button. Works with Request triggers (HTTP request, manual Button, PowerApps) and with scheduled RECURRENCE flows, which run immediately; a scheduled flow takes no inputs, so passing `body` to one is refused. Pass trigger inputs as `body`. Automated connector triggers only fire from their source event.
| Parameter | Type | Description |
|---|---|---|
| body | object | JSON body to POST to the trigger URL. Omit for flows that expect an empty body. |
| flowName * | string | Name (ID) of the flow. |
| connections | object | Only for a flow whose connections are provided by whoever runs it. Map of connection-reference name to the connection id to run it with, e.g. {"shared_office365users":"shared-office365user-…"}. Omit unless the result told you the connection picked was wrong; ids come from list_live_connections. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "trigger_live_flow",
"title": "Run flow",
"description": "Run a flow on demand — the same as the maker portal's \"Run flow\" button. Works with Request triggers (HTTP request, manual Button, PowerApps) and with scheduled RECURRENCE flows, which run immediately; a scheduled flow takes no inputs, so passing `body` to one is refused. Pass trigger inputs as `body`. Automated connector triggers only fire from their source event.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName"
],
"properties": {
"body": {
"type": "object",
"description": "JSON body to POST to the trigger URL. Omit for flows that expect an empty body.",
"additionalProperties": true
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"connections": {
"type": "object",
"description": "Only for a flow whose connections are provided by whoever runs it. Map of connection-reference name to the connection id to run it with, e.g. {\"shared_office365users\":\"shared-office365user-…\"}. Omit unless the result told you the connection picked was wrong; ids come from list_live_connections.",
"additionalProperties": {
"type": "string"
}
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Run flow",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Cancel a currently running Power Automate flow run via the live PA API. Use after get_live_flow_runs to obtain the run name. Only runs with status "Running" can be cancelled.
| Parameter | Type | Description |
|---|---|---|
| runName * | string | Run identifier (name field from get_live_flow_runs). |
| flowName * | string | Name (ID) of the flow. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "cancel_live_flow_run",
"title": "Cancel run",
"description": "Cancel a currently running Power Automate flow run via the live PA API. Use after get_live_flow_runs to obtain the run name. Only runs with status \"Running\" can be cancelled.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName",
"runName"
],
"properties": {
"runName": {
"type": "string",
"description": "Run identifier (name field from get_live_flow_runs)."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Cancel run",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}Resubmit a failed or cancelled Power Automate flow run via the live PA API, re-using the original trigger payload. Discovers the trigger name from the flow definition automatically — no trigger name parameter needed.
| Parameter | Type | Description |
|---|---|---|
| runName * | string | Run identifier (name field from get_live_flow_runs), or "latest" for the most recent run. |
| flowName * | string | Name (ID) of the flow. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "resubmit_live_flow_run",
"title": "Resubmit run",
"description": "Resubmit a failed or cancelled Power Automate flow run via the live PA API, re-using the original trigger payload. Discovers the trigger name from the flow definition automatically — no trigger name parameter needed.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName",
"runName"
],
"properties": {
"runName": {
"type": "string",
"description": "Run identifier (name field from get_live_flow_runs), or \"latest\" for the most recent run."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Resubmit run",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Start or stop the flow you name. Reads the current state first and only calls Power Automate if a change is actually needed.
| Parameter | Type | Description |
|---|---|---|
| state * | string | Desired state for the flow. |
| flowName * | string | Name (ID) of the flow. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "set_live_flow_state",
"title": "Turn flow on or off",
"description": "Start or stop the flow you name. Reads the current state first and only calls Power Automate if a change is actually needed.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName",
"state"
],
"properties": {
"state": {
"enum": [
"Started",
"Stopped"
],
"type": "string",
"description": "Desired state for the flow."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Turn flow on or off",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fetch the full native Power Automate flow JSON from the PA API, including the complete flow definition (triggers, actions, parameters, outputs). Returns the raw properties object exactly as the PA API returns it. Use this to inspect the full definition before calling update_live_flow with a modified definition.
| Parameter | Type | Description |
|---|---|---|
| depth | string | full (default): the whole definition. summary: the action tree — name, type, operation, runAfter, nesting — with no inputs. Use summary on a large flow, then ask for the actions you need. |
| actions | array | Return only these actions, found at any nesting depth and each reported with the scopes it sits in, plus triggers. Combine with depth:"summary" to get the tree as well. |
| version | string | An earlier version to read instead of the current flow: a version from get_live_flow_versions, or a date. |
| flowName * | string | Name (ID) of the flow. |
| environmentName * | string | Name of the Power Platform environment. |
| includeTriggerUrl | boolean | Also return the HTTP trigger URL. It is a credential: anyone holding it can run the flow. |
{
"name": "get_live_flow",
"title": "Get flow definition",
"description": "Fetch the full native Power Automate flow JSON from the PA API, including the complete flow definition (triggers, actions, parameters, outputs). Returns the raw properties object exactly as the PA API returns it. Use this to inspect the full definition before calling update_live_flow with a modified definition.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName"
],
"properties": {
"depth": {
"enum": [
"summary",
"full"
],
"type": "string",
"description": "full (default): the whole definition. summary: the action tree — name, type, operation, runAfter, nesting — with no inputs. Use summary on a large flow, then ask for the actions you need."
},
"actions": {
"type": "array",
"items": {
"type": "string"
},
"description": "Return only these actions, found at any nesting depth and each reported with the scopes it sits in, plus triggers. Combine with depth:\"summary\" to get the tree as well."
},
"version": {
"type": "string",
"description": "An earlier version to read instead of the current flow: a version from get_live_flow_versions, or a date."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
},
"includeTriggerUrl": {
"type": "boolean",
"description": "Also return the HTTP trigger URL. It is a credential: anyone holding it can run the flow."
}
}
},
"annotations": {
"title": "Get flow definition",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List a flow's versions, newest first. A flow in a solution lists every published version. Any other flow lists only versions that ran.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max versions to return. Default 30. |
| flowName * | string | Name (ID) of the flow. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "get_live_flow_versions",
"title": "List flow versions",
"description": "List a flow's versions, newest first. A flow in a solution lists every published version. Any other flow lists only versions that ran.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName"
],
"properties": {
"top": {
"type": "number",
"description": "Max versions to return. Default 30."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "List flow versions",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Compare two versions of a flow. Returns the actions added, removed and changed.
| Parameter | Type | Description |
|---|---|---|
| to | string | The later version, in the same form. Default: the current flow. |
| from * | string | The earlier version: a version from get_live_flow_versions, or a date. |
| flowName * | string | Name (ID) of the flow. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "diff_live_flow",
"title": "Compare flow versions",
"description": "Compare two versions of a flow. Returns the actions added, removed and changed.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName",
"from"
],
"properties": {
"to": {
"type": "string",
"description": "The later version, in the same form. Default: the current flow."
},
"from": {
"type": "string",
"description": "The earlier version: a version from get_live_flow_versions, or a date."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Compare flow versions",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Update or create a flow. Use `dryRun: true` to preview any change without writing. Omit flowName to create: definition and displayName are required. Give flowName to update: displayName and/or definition and/or connectionReferences. SURGICAL EDIT: pass `operations` — an ordered list of set/add/remove/merge ops on array-of-keys paths — to change one action or parameter without resending the whole definition. Provide EITHER operations OR definition; connectionReferences may accompany either and lands in the same save. WHOLE definition: call get_live_flow, mutate properties.definition, pass it here. RENAME: pass displayName alone. Power Automate rejects a PATCH carrying no flow content, so this re-saves the unchanged definition — the maker portal does the same. definition.description is required, and must be brief — we append " #flowstudio-mcp" to it.
| Parameter | Type | Description |
|---|---|---|
| dryRun | boolean | Preview only, on BOTH paths: with flowName, apply the change to the live definition and return the result + what changed; without flowName, return the flow that WOULD be created. Nothing is written either way. |
| flowName | string | Name (ID) of the flow to update. Omit or leave blank to create a new flow. |
| definition | object | Full flow definition as a JSON object (triggers + actions + parameters + outputs + description). MUST be a JSON object — strings are rejected. Do not JSON.stringify the definition; pass the parsed object directly. Required when creating. For updates, obtain from get_live_flow (properties.definition)… |
| operations | array | SURGICAL EDIT of an existing flow (requires flowName; do not combine with definition). An ordered list applied to the LIVE definition. Each item = { op, path, value? }. path is an ARRAY of literal keys, e.g. ["actions","Send_Email","inputs","parameters","subject"] (each element is one key; a "/" ins… |
| displayName | string | Display name for the flow. Required when creating. |
| discardDraft | boolean | If an unpublished draft blocks the save, discard it and save again. The draft stays in the flow's version history. |
| environmentName * | string | Name of the Power Platform environment. |
| connectionReferences | object | Connection references map copied from get_live_flow. Direct-flow entries use { connectionName, id }. Solution-aware entries also include { connectionReferenceLogicalName, source } and must retain those fields exactly. A freshly migrated entry may instead be keyed by the physical connection name and … |
| expectedLastModifiedTime | string | With a whole definition: refuse if the flow changed since you read it. Pass get_live_flow's lastModifiedTime. |
{
"name": "update_live_flow",
"title": "Create or update flow",
"description": "Update or create a flow. Use `dryRun: true` to preview any change without writing. Omit flowName to create: definition and displayName are required. Give flowName to update: displayName and/or definition and/or connectionReferences. SURGICAL EDIT: pass `operations` — an ordered list of set/add/remove/merge ops on array-of-keys paths — to change one action or parameter without resending the whole definition. Provide EITHER operations OR definition; connectionReferences may accompany either and lands in the same save. WHOLE definition: call get_live_flow, mutate properties.definition, pass it here. RENAME: pass displayName alone. Power Automate rejects a PATCH carrying no flow content, so this re-saves the unchanged definition — the maker portal does the same. definition.description is required, and must be brief — we append \" #flowstudio-mcp\" to it.",
"inputSchema": {
"type": "object",
"required": [
"environmentName"
],
"properties": {
"dryRun": {
"type": "boolean",
"description": "Preview only, on BOTH paths: with flowName, apply the change to the live definition and return the result + what changed; without flowName, return the flow that WOULD be created. Nothing is written either way."
},
"flowName": {
"type": "string",
"description": "Name (ID) of the flow to update. Omit or leave blank to create a new flow."
},
"definition": {
"type": "object",
"description": "Full flow definition as a JSON object (triggers + actions + parameters + outputs + description). MUST be a JSON object — strings are rejected. Do not JSON.stringify the definition; pass the parsed object directly. Required when creating. For updates, obtain from get_live_flow (properties.definition), modify it, then pass the modified object here. definition.description is required (a short note about what changed); when updating, if you omit it we reuse the flow's existing description.",
"additionalProperties": true
},
"operations": {
"type": "array",
"items": {
"type": "object",
"required": [
"op",
"path"
],
"properties": {
"op": {
"enum": [
"set",
"add",
"remove",
"merge"
],
"type": "string",
"description": "Edit verb."
},
"path": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer",
"minimum": 0
}
]
},
"description": "Array of literal keys, one per level, e.g. [\"actions\",\"Compose\",\"inputs\"]. Inside an array, use the item index: [\"actions\",\"Condition\",\"expression\",\"and\",0]. A \"/\" inside an element is a literal character, so SharePoint/Dataverse column params (flat keys like \"item/Title\") are addressable: [\"actions\",\"Update_Item\",\"inputs\",\"parameters\",\"item/Title\"]. Do NOT pass a slash-delimited string — it cannot distinguish a literal \"/\" from a separator."
},
"value": {
"anyOf": [
{
"type": "string"
},
{
"type": "number"
},
{
"type": "boolean"
},
{
"type": "null"
},
{
"type": "object",
"additionalProperties": true
},
{
"type": "array",
"items": {}
}
],
"description": "New value (required for set/add/merge; merge requires an object)."
}
}
},
"description": "SURGICAL EDIT of an existing flow (requires flowName; do not combine with definition). An ordered list applied to the LIVE definition. Each item = { op, path, value? }. path is an ARRAY of literal keys, e.g. [\"actions\",\"Send_Email\",\"inputs\",\"parameters\",\"subject\"] (each element is one key; a \"/\" inside an element is literal, so it addresses SharePoint/Dataverse columns like [\"actions\",\"Update_Item\",\"inputs\",\"parameters\",\"item/Title\"]). ops: set (create/overwrite), add (new key — errors if it already exists), remove (delete key — no-op if absent), merge (deep-merge an object value, keeping sibling keys)."
},
"displayName": {
"type": "string",
"description": "Display name for the flow. Required when creating."
},
"discardDraft": {
"type": "boolean",
"description": "If an unpublished draft blocks the save, discard it and save again. The draft stays in the flow's version history."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
},
"connectionReferences": {
"type": "object",
"description": "Connection references map copied from get_live_flow. Direct-flow entries use { connectionName, id }. Solution-aware entries also include { connectionReferenceLogicalName, source } and must retain those fields exactly. A freshly migrated entry may instead be keyed by the physical connection name and carry no connectionName field at all — copy it back as-is. The action/trigger inputs.host.connectionName must match the map key; the physical connectionName stays inside the entry. Never invent a solution logical name. Adding a connectionReferenceLogicalName to an entry that lacks one does not always take: the save can return success without storing it, so re-read with get_live_flow to confirm. MAY BE PASSED ALONGSIDE operations: your entries are merged over the stored map and saved in the SAME request as the edit. That is how you add the first action for a connector the flow does not use yet — a reference saved on its own does not stick, because Power Automate prunes an entry no action references. Your entries win on a key collision.",
"additionalProperties": true
},
"expectedLastModifiedTime": {
"type": "string",
"description": "With a whole definition: refuse if the flow changed since you read it. Pass get_live_flow's lastModifiedTime."
}
}
},
"annotations": {
"title": "Create or update flow",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}List all Power Platform environments you belong to, directly from Power Automate. Returns id, displayName, sku, location, and state for each environment. mode=all (default) and mode=member: every environment you are a member of. mode=admin: only those you administer; errors rather than guessing if admin access cannot be determined. isAdmin means you hold the ListAnyFlow permission there — the capability list_live_flows mode=admin needs. It is null, never false, when the platform did not tell us. isMember is true for every environment returned.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max environments to return. Paginates automatically. Omit for all. |
| mode | string | all (default) and member: every environment you belong to. admin: only those where you hold ListAnyFlow; errors rather than returning a shorter list if admin access cannot be determined. |
{
"name": "list_live_environments",
"title": "List environments",
"description": "List all Power Platform environments you belong to, directly from Power Automate. Returns id, displayName, sku, location, and state for each environment. mode=all (default) and mode=member: every environment you are a member of. mode=admin: only those you administer; errors rather than guessing if admin access cannot be determined. isAdmin means you hold the ListAnyFlow permission there — the capability list_live_flows mode=admin needs. It is null, never false, when the platform did not tell us. isMember is true for every environment returned.",
"inputSchema": {
"type": "object",
"properties": {
"top": {
"type": "number",
"description": "Max environments to return. Paginates automatically. Omit for all."
},
"mode": {
"enum": [
"all",
"member",
"admin"
],
"type": "string",
"description": "all (default) and member: every environment you belong to. admin: only those where you hold ListAnyFlow; errors rather than returning a shorter list if admin access cannot be determined."
}
}
},
"annotations": {
"title": "List environments",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List Power Automate flows in an environment. Returns id, displayName, state, triggerType, and lastModifiedTime for each flow. mode=owner (default): flows you own plus flows shared with you (personal + team), with full definitions. mode=admin: all flows in the environment (requires an admin account). mode=admin with includeDeleted=true also returns soft-deleted flows (state=Deleted) — the only way to find a deleted flow. If search is provided, results are filtered to flows whose displayName contains the search text. For large environments pagination is time-bounded — if nextLink is returned, pass it as continuationUrl to retrieve the next batch.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max flows to return. Paginates automatically. Omit for all. |
| mode | string | owner (default): user-scoped — owned + shared-with-me flows (personal + team), with full definitions. admin: admin-scoped endpoint, all flows. |
| search | string | Optional case-insensitive filter applied to flow displayName. |
| includeDeleted | boolean | Include soft-deleted flows, which come back with state=Deleted and can be restored with restore_live_flow. Requires mode=admin — the user-scoped listing never returns deleted flows. Off by default. |
| timeoutSeconds | number | Stop collecting pages after this many seconds and return a nextLink for the next batch. Default 25. Max 55. |
| continuationUrl | string | nextLink value returned by a previous call. Pass to resume pagination from where the last call stopped. Must match the same mode as the original call. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "list_live_flows",
"title": "List flows",
"description": "List Power Automate flows in an environment. Returns id, displayName, state, triggerType, and lastModifiedTime for each flow. mode=owner (default): flows you own plus flows shared with you (personal + team), with full definitions. mode=admin: all flows in the environment (requires an admin account). mode=admin with includeDeleted=true also returns soft-deleted flows (state=Deleted) — the only way to find a deleted flow. If search is provided, results are filtered to flows whose displayName contains the search text. For large environments pagination is time-bounded — if nextLink is returned, pass it as continuationUrl to retrieve the next batch.",
"inputSchema": {
"type": "object",
"required": [
"environmentName"
],
"properties": {
"top": {
"type": "number",
"description": "Max flows to return. Paginates automatically. Omit for all."
},
"mode": {
"enum": [
"owner",
"admin"
],
"type": "string",
"description": "owner (default): user-scoped — owned + shared-with-me flows (personal + team), with full definitions. admin: admin-scoped endpoint, all flows."
},
"search": {
"type": "string",
"description": "Optional case-insensitive filter applied to flow displayName."
},
"includeDeleted": {
"type": "boolean",
"description": "Include soft-deleted flows, which come back with state=Deleted and can be restored with restore_live_flow. Requires mode=admin — the user-scoped listing never returns deleted flows. Off by default."
},
"timeoutSeconds": {
"type": "number",
"description": "Stop collecting pages after this many seconds and return a nextLink for the next batch. Default 25. Max 55."
},
"continuationUrl": {
"type": "string",
"description": "nextLink value returned by a previous call. Pass to resume pagination from where the last call stopped. Must match the same mode as the original call."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "List flows",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}List Power Platform connections in an environment directly from Power Automate. Returns id, displayName, connectorName, environment, createdBy (full object), authenticatedUser, statuses, overallStatus, createdTime, expirationTime, and connectionParameters for each connection. Pass search=<term> to narrow the list and receive a paste-ready connectionReferenceTemplate plus action-side hostTemplate per connection — drop these into update_live_flow's connectionReferences and inputs.host without further edits.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max connections to RETURN, applied after search. Paginates automatically. Omit for all. |
| search | string | Optional case-insensitive substring filter applied to id, displayName, connectorName, and accountName. Adds connectionReferenceTemplate + hostTemplate to each returned connection. |
| environmentName * | string | Required. Name of the Power Platform environment (a GUID, or a name like "Default-<tid>"). Call list_live_environments if you do not have one — the platform cannot list connections across environments. |
{
"name": "list_live_connections",
"title": "List connections",
"description": "List Power Platform connections in an environment directly from Power Automate. Returns id, displayName, connectorName, environment, createdBy (full object), authenticatedUser, statuses, overallStatus, createdTime, expirationTime, and connectionParameters for each connection. Pass search=<term> to narrow the list and receive a paste-ready connectionReferenceTemplate plus action-side hostTemplate per connection — drop these into update_live_flow's connectionReferences and inputs.host without further edits.",
"inputSchema": {
"type": "object",
"required": [
"environmentName"
],
"properties": {
"top": {
"type": "number",
"description": "Max connections to RETURN, applied after search. Paginates automatically. Omit for all."
},
"search": {
"type": "string",
"description": "Optional case-insensitive substring filter applied to id, displayName, connectorName, and accountName. Adds connectionReferenceTemplate + hostTemplate to each returned connection."
},
"environmentName": {
"type": "string",
"description": "Required. Name of the Power Platform environment (a GUID, or a name like \"Default-<tid>\"). Call list_live_environments if you do not have one — the platform cannot list connections across environments."
}
}
},
"annotations": {
"title": "List connections",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Describe a live Power Platform connector/API and its operations. Use mode=summary (default) to get a compact operation catalog. Use operationId to describe one operation, including inputs, outputs, dynamic parameter metadata, nextTool hints to call resolve_live_parameters, and an authored hint + canonical example shape (when one exists) to copy into update_live_flow. Use search without connectorName/apiName to search operations across connectors and get connection-aware suggestions. Use mode=full only when raw OpenAPI connector metadata is required.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max operations to return in connector summary mode, or max top search results to show in cross-connector search. Default 250 for summary, 10 for search display. |
| type | string | Operation usage to include in summary mode. Default Action. |
| depth | string | summary (default): compact operation catalog. full: raw OpenAPI metadata. |
| search | string | Optional operation search text. With connectorName, filters that connector summary. Without connectorName, searches operations across connectors. |
| apiName | string | Alias for connectorName. |
| variant | string | When an operation has multiple authored variants (e.g. shared_teams/PostMessageToConversation has channel/groupchat/flowbot_chat), pass a specific variantKey to get that variant's hint and exampleDefinition. Omit to receive a hint listing the available variants. |
| operationId | string | Optional operation ID to describe with expanded inputs and outputs. |
| connectorName | string | Connector logical name, for example shared_teams. Either connectorName/apiName is required, unless search is provided for cross-connector operation search. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "describe_live_connector",
"title": "Describe connector",
"description": "Describe a live Power Platform connector/API and its operations. Use mode=summary (default) to get a compact operation catalog. Use operationId to describe one operation, including inputs, outputs, dynamic parameter metadata, nextTool hints to call resolve_live_parameters, and an authored hint + canonical example shape (when one exists) to copy into update_live_flow. Use search without connectorName/apiName to search operations across connectors and get connection-aware suggestions. Use mode=full only when raw OpenAPI connector metadata is required.",
"inputSchema": {
"type": "object",
"required": [
"environmentName"
],
"properties": {
"top": {
"type": "number",
"description": "Max operations to return in connector summary mode, or max top search results to show in cross-connector search. Default 250 for summary, 10 for search display."
},
"type": {
"enum": [
"Action",
"Trigger"
],
"type": "string",
"description": "Operation usage to include in summary mode. Default Action."
},
"depth": {
"enum": [
"summary",
"full"
],
"type": "string",
"description": "summary (default): compact operation catalog. full: raw OpenAPI metadata."
},
"search": {
"type": "string",
"description": "Optional operation search text. With connectorName, filters that connector summary. Without connectorName, searches operations across connectors."
},
"apiName": {
"type": "string",
"description": "Alias for connectorName."
},
"variant": {
"type": "string",
"description": "When an operation has multiple authored variants (e.g. shared_teams/PostMessageToConversation has channel/groupchat/flowbot_chat), pass a specific variantKey to get that variant's hint and exampleDefinition. Omit to receive a hint listing the available variants."
},
"operationId": {
"type": "string",
"description": "Optional operation ID to describe with expanded inputs and outputs."
},
"connectorName": {
"type": "string",
"description": "Connector logical name, for example shared_teams. Either connectorName/apiName is required, unless search is provided for cross-connector operation search."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Describe connector",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Add a flow or a canvas app to a solution. Pass flowName or app. A flow not yet in a solution moves into `solution`, or into the default solution when it is omitted. A flow or app already in a solution is added to `solution` as well, and stays in the one it is in.
| Parameter | Type | Description |
|---|---|---|
| app | string | The canvas app (ID). Not with flowName. |
| flowName | string | The flow (ID). Not with app. |
| solution | string | The solution: its unique name, or its solutionid GUID. Required for an app, and for a flow already in a solution. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "add_to_solution",
"title": "Add to solution",
"description": "Add a flow or a canvas app to a solution. Pass flowName or app. A flow not yet in a solution moves into `solution`, or into the default solution when it is omitted. A flow or app already in a solution is added to `solution` as well, and stays in the one it is in.",
"inputSchema": {
"type": "object",
"required": [
"environmentName"
],
"properties": {
"app": {
"type": "string",
"description": "The canvas app (ID). Not with flowName."
},
"flowName": {
"type": "string",
"description": "The flow (ID). Not with app."
},
"solution": {
"type": "string",
"description": "The solution: its unique name, or its solutionid GUID. Required for an app, and for a flow already in a solution."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Add to solution",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Resolve a connector action's inputs the way the flow designer does: dropdown options, list and table columns, folder and file pickers — every input in one call, or one with parameterName. Reads only: it runs the lookups the designer runs, never an action. Pass values you have in parameters; pass a display name in match to get back the value to write into the flow. An input whose parent is not known yet has status "needs". Inputs inside an object are addressed by key (body/recipient/groupId). Omit connectionName and one is chosen.
| Parameter | Type | Description |
|---|---|---|
| top | number | Max options per dropdown (default 200). A longer list is marked truncated. |
| skip | number | Options to skip, to page through a truncated list (use nextSkip). |
| match | object | Exact display name, or the value itself, per input, e.g. { "folderPath": "Inbox" }. Case-insensitive, never fuzzy. Folders also take /path. matchCount 0 answers status "nomatch". |
| browse | object | Open a folder: { "field": "<input>", "id": "<folder value>" }. |
| detail | string | Column detail. Default compact. |
| search | string | Narrow long option or column lists by name (a filter, not a pick). |
| apiName | string | Alias for connectorName. |
| include | array | Add "outputs" to get the fields this action returns. |
| flowName | string | With actionName: take the connector, operation and connection from this flow action. |
| actionName | string | Action (or trigger) name in flowName. |
| parameters | object | Values already chosen, e.g. { "dataset": "<site url>" }. |
| operationId | string | Operation ID, e.g. PostItem. Not needed with flowName + actionName. |
| connectorName | string | Connector name, e.g. shared_sharepointonline. |
| parameterName | string | Resolve only this input. Omit for every input. |
| connectionName | string | Connection to run as. Omit to have one chosen. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "resolve_live_parameters",
"title": "Resolve action inputs",
"description": "Resolve a connector action's inputs the way the flow designer does: dropdown options, list and table columns, folder and file pickers — every input in one call, or one with parameterName. Reads only: it runs the lookups the designer runs, never an action. Pass values you have in parameters; pass a display name in match to get back the value to write into the flow. An input whose parent is not known yet has status \"needs\". Inputs inside an object are addressed by key (body/recipient/groupId). Omit connectionName and one is chosen.",
"inputSchema": {
"type": "object",
"required": [
"environmentName"
],
"properties": {
"top": {
"type": "number",
"description": "Max options per dropdown (default 200). A longer list is marked truncated."
},
"skip": {
"type": "number",
"description": "Options to skip, to page through a truncated list (use nextSkip)."
},
"match": {
"type": "object",
"description": "Exact display name, or the value itself, per input, e.g. { \"folderPath\": \"Inbox\" }. Case-insensitive, never fuzzy. Folders also take /path. matchCount 0 answers status \"nomatch\".",
"additionalProperties": true
},
"browse": {
"type": "object",
"description": "Open a folder: { \"field\": \"<input>\", \"id\": \"<folder value>\" }.",
"additionalProperties": true
},
"detail": {
"enum": [
"compact",
"full"
],
"type": "string",
"description": "Column detail. Default compact."
},
"search": {
"type": "string",
"description": "Narrow long option or column lists by name (a filter, not a pick)."
},
"apiName": {
"type": "string",
"description": "Alias for connectorName."
},
"include": {
"type": "array",
"items": {
"enum": [
"outputs"
],
"type": "string"
},
"description": "Add \"outputs\" to get the fields this action returns."
},
"flowName": {
"type": "string",
"description": "With actionName: take the connector, operation and connection from this flow action."
},
"actionName": {
"type": "string",
"description": "Action (or trigger) name in flowName."
},
"parameters": {
"type": "object",
"description": "Values already chosen, e.g. { \"dataset\": \"<site url>\" }.",
"additionalProperties": true
},
"operationId": {
"type": "string",
"description": "Operation ID, e.g. PostItem. Not needed with flowName + actionName."
},
"connectorName": {
"type": "string",
"description": "Connector name, e.g. shared_sharepointonline."
},
"parameterName": {
"type": "string",
"description": "Resolve only this input. Omit for every input."
},
"connectionName": {
"type": "string",
"description": "Connection to run as. Omit to have one chosen."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Resolve action inputs",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Test a connection, or run one operation on it. Without operationId it runs the connector's own connection test. With operationId it runs that operation and returns the raw reply: a GET operation, or a lookup the connector itself declares for a dropdown, list, schema or folder picker. Anything else is refused before a call is made. connectionName comes from list_live_connections; operation ids from describe_live_connector.
| Parameter | Type | Description |
|---|---|---|
| parameters | object | The operation's inputs by name (path, query, header or body). |
| operationId | string | Omit to run the connector's own connection test. |
| connectorName * | string | Connector name, e.g. shared_sharepointonline. |
| connectionName * | string | The connection, from list_live_connections. |
| continuationUrl | string | The nextLink from the previous reply, to fetch the next page. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "test_live_connection",
"title": "Test connection",
"description": "Test a connection, or run one operation on it. Without operationId it runs the connector's own connection test. With operationId it runs that operation and returns the raw reply: a GET operation, or a lookup the connector itself declares for a dropdown, list, schema or folder picker. Anything else is refused before a call is made. connectionName comes from list_live_connections; operation ids from describe_live_connector.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"connectorName",
"connectionName"
],
"properties": {
"parameters": {
"type": "object",
"description": "The operation's inputs by name (path, query, header or body).",
"additionalProperties": true
},
"operationId": {
"type": "string",
"description": "Omit to run the connector's own connection test."
},
"connectorName": {
"type": "string",
"description": "Connector name, e.g. shared_sharepointonline."
},
"connectionName": {
"type": "string",
"description": "The connection, from list_live_connections."
},
"continuationUrl": {
"type": "string",
"description": "The nextLink from the previous reply, to fetch the next page."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Test connection",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Create a connection, or sign an existing one in again (pass connectionName). Shows a sign-in card where the person signs in; you never sign in for them. Without the card, give the person signInLink to open. Connectors that use a key or account details instead of a sign-in are refused: create those in Power Automate.
| Parameter | Type | Description |
|---|---|---|
| connectorName * | string | Connector name, e.g. shared_sharepointonline. |
| connectionName | string | An existing connection to sign in again, instead of creating one. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "create_live_connection",
"title": "Create connection",
"description": "Create a connection, or sign an existing one in again (pass connectionName). Shows a sign-in card where the person signs in; you never sign in for them. Without the card, give the person signInLink to open. Connectors that use a key or account details instead of a sign-in are refused: create those in Power Automate.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"connectorName"
],
"properties": {
"connectorName": {
"type": "string",
"description": "Connector name, e.g. shared_sharepointonline."
},
"connectionName": {
"type": "string",
"description": "An existing connection to sign in again, instead of creating one."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Create connection",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Read rows from a Dataverse table, SharePoint list, SQL table or Excel table. Read-only. Returns rows, columns and nextLink.
| Parameter | Type | Description |
|---|---|---|
| top | number | Rows, 1 to 100. Default 20. |
| skip | number | SQL and Excel: rows to skip, for the next page. |
| table * | string | Dataverse: the set name, e.g. accounts. SharePoint: the list title or id. SQL or Excel: the table. |
| filter | string | An OData filter. |
| select | string | Comma-separated columns. |
| dataset | string | Where the table lives. SharePoint: the site URL. SQL: server,database. Excel: drive,file. |
| connector | string | Omit for Dataverse. |
| connection | string | The connection name, when you have more than one. |
| continuationUrl | string | The nextLink from the previous reply, for the next page. |
| environmentName * | string | Name of the Power Platform environment. |
{
"name": "read_live_table",
"title": "Read table rows",
"description": "Read rows from a Dataverse table, SharePoint list, SQL table or Excel table. Read-only. Returns rows, columns and nextLink.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"table"
],
"properties": {
"top": {
"type": "number",
"description": "Rows, 1 to 100. Default 20."
},
"skip": {
"type": "number",
"description": "SQL and Excel: rows to skip, for the next page."
},
"table": {
"type": "string",
"description": "Dataverse: the set name, e.g. accounts. SharePoint: the list title or id. SQL or Excel: the table."
},
"filter": {
"type": "string",
"description": "An OData filter."
},
"select": {
"type": "string",
"description": "Comma-separated columns."
},
"dataset": {
"type": "string",
"description": "Where the table lives. SharePoint: the site URL. SQL: server,database. Excel: drive,file."
},
"connector": {
"enum": [
"sharepoint",
"sql",
"excel"
],
"type": "string",
"description": "Omit for Dataverse."
},
"connection": {
"type": "string",
"description": "The connection name, when you have more than one."
},
"continuationUrl": {
"type": "string",
"description": "The nextLink from the previous reply, for the next page."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
}
}
},
"annotations": {
"title": "Read table rows",
"readOnlyHint": true,
"openWorldHint": false,
"destructiveHint": false
}
}Shows a sign-in card; the person signs in, or signs in again when expired. Flow Studio keeps the sign-in for later calls.
No parameters.
{
"name": "grant_flow_studio_access",
"title": "Grant Flow Studio access",
"description": "Shows a sign-in card; the person signs in, or signs in again when expired. Flow Studio keeps the sign-in for later calls.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "Grant Flow Studio access",
"readOnlyHint": false,
"openWorldHint": false,
"destructiveHint": false
}
}Delete a Power Automate cloud flow. DESTRUCTIVE and not discoverable afterwards. Requires confirmDisplayName (the flow's exact displayName, from get_live_flow) and a reason, which is recorded in the audit log. A deleted flow CAN be restored with restore_live_flow using the flowName returned here. If the id is lost, only an environment admin can recover it — list_live_flows mode=admin includeDeleted=true is the only listing that returns deleted flows. If you only want the flow to stop running, use set_live_flow_state with state=Stopped instead. Works only while the user has Delete Lock off; otherwise the call is refused and nothing is deleted.
| Parameter | Type | Description |
|---|---|---|
| reason * | string | Short note on why this flow is being deleted. Recorded in the audit log. |
| flowName * | string | The flow id to delete. |
| environmentName * | string | Name of the Power Platform environment. |
| confirmDisplayName * | string | The flow's exact displayName, as returned by get_live_flow. Must match, or the call is refused and nothing is deleted. |
{
"name": "delete_live_flow",
"title": "Delete flow",
"description": "Delete a Power Automate cloud flow. DESTRUCTIVE and not discoverable afterwards. Requires confirmDisplayName (the flow's exact displayName, from get_live_flow) and a reason, which is recorded in the audit log. A deleted flow CAN be restored with restore_live_flow using the flowName returned here. If the id is lost, only an environment admin can recover it — list_live_flows mode=admin includeDeleted=true is the only listing that returns deleted flows. If you only want the flow to stop running, use set_live_flow_state with state=Stopped instead. Works only while the user has Delete Lock off; otherwise the call is refused and nothing is deleted.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName",
"confirmDisplayName",
"reason"
],
"properties": {
"reason": {
"type": "string",
"description": "Short note on why this flow is being deleted. Recorded in the audit log."
},
"flowName": {
"type": "string",
"description": "The flow id to delete."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment."
},
"confirmDisplayName": {
"type": "string",
"description": "The flow's exact displayName, as returned by get_live_flow. Must match, or the call is refused and nothing is deleted."
}
}
},
"annotations": {
"title": "Delete flow",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Restore a deleted Power Automate cloud flow, using its flow id. Take the id from the delete_live_flow response, your own notes, or — with an admin account — list_live_flows with mode=admin and includeDeleted=true, the only listing that returns deleted flows (they come back with state=Deleted). The user-scoped listing never shows them. Restore can complete asynchronously — confirm with get_live_flow. The restore window is limited and its length is not documented, so restore promptly.
| Parameter | Type | Description |
|---|---|---|
| flowName * | string | The id of the deleted flow. Cannot be looked up — nothing lists deleted flows. |
| environmentName * | string | Name of the Power Platform environment the flow was deleted from. |
{
"name": "restore_live_flow",
"title": "Restore deleted flow",
"description": "Restore a deleted Power Automate cloud flow, using its flow id. Take the id from the delete_live_flow response, your own notes, or — with an admin account — list_live_flows with mode=admin and includeDeleted=true, the only listing that returns deleted flows (they come back with state=Deleted). The user-scoped listing never shows them. Restore can complete asynchronously — confirm with get_live_flow. The restore window is limited and its length is not documented, so restore promptly.",
"inputSchema": {
"type": "object",
"required": [
"environmentName",
"flowName"
],
"properties": {
"flowName": {
"type": "string",
"description": "The id of the deleted flow. Cannot be looked up — nothing lists deleted flows."
},
"environmentName": {
"type": "string",
"description": "Name of the Power Platform environment the flow was deleted from."
}
}
},
"annotations": {
"title": "Restore deleted flow",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Flow Studio MCP inspects and modifies Microsoft Power Automate flows. When the user request maps to one of these named workflows, prefer the matching skill bundle: - diagnose-connection-references: Diagnose and fix connection-reference problems on flows in solutions. - dataverse: Work with Dataverse tables in flows and canvas apps: find tables, columns and choice values. - sharepoint: Work with SharePoint lists in flows and canvas apps: find sites, lists, columns and choice values. - excel: Work with Excel tables in flows and canvas apps: find files, tables and columns. - sql: Work with SQL tables in flows and canvas apps: find databases, tables and columns. - build-flow: Read or modify an existing flow definition, including an action's live dropdown and column values. - flow-versions: See earlier versions of a flow, compare them, and put an earlier version back. - create-flow: Create a new flow from scratch: connector examples, connections and live input values. - debug-flow: Investigate why a flow is failing: recent runs, the failed run, and the failing action's inputs and outputs. - monitor-flow: Runtime control of a flow: start/stop, trigger, cancel or resubmit a run. - discover: Cold-start enumeration of a tenant: what environments, flows and connections exist. - governance: Tag, monitor and audit flows from the cached store (Pro+ only; not available over SSO). To find the right tool, use the meta-tools: - `list_skills` — enumerate the bundles above with their member tools - `tool_search` — fetch tool schemas by skill, exact selector, or free-text query: "skill:debug-flow" (a whole bundle) query: "select:get_live_flow,update_live_flow" (exact tools) query: "cancel run" (keyword match) If a tool misbehaves or a capability is missing, call `report_bug` — it is free and can attach session diagnostics. All three support/meta-tools are non-billable and remain available after quota exhaustion. Prefer them over guessing tool names. If a reply names another tool to use, switch to it: the one you called is being retired.
Names, descriptions and schemas were written by the server and are shown as data.