spendctl is an MCP server published by dev.spendctl, hosted at mcp.spendctl.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 8 tools, including sandbox_create, sandbox_pay, await_approval, withdraw_approval, check_budget.
Spend policy for AI agents that pay (x402, MPP). Login-free sandbox, real sidecar, no real funds.
Nothing else in the archive shares these values.
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.
Creates an isolated spendctl sandbox and returns its sandbox_id. Call it first: every other tool needs the sandbox_id, and one sandbox serves a whole conversation (create another only to try a different preset). The sandbox is a real spendctl sidecar with a throwaway wallet, a mock x402 facilitator and two mock paid APIs; no real money moves and nothing outside the sandbox is reachable. Returns the sandbox_id, the agent's policy (budgets, allowed hosts, approval rule) and the paid endpoints with their prices. Limits: 5 sandboxes per minute per client address (claude.ai users share addresses and get a larger allowance); a sandbox expires after 2 hours without calls (24 hours at most). Example: preset "strict" to see refusals, "approvals" to see a payment held for a human.
| Parameter | Type | Description |
|---|---|---|
| preset | string | Policy preset. default: comfortable caps, both endpoints allowed; strict: $0.015 per request and $0.03 per day, weather only, so the search API and a fourth weather call are refused; approvals: payments at or above $0.015 wait for approve |
{
"name": "sandbox_create",
"title": "Create a spendctl sandbox",
"description": "Creates an isolated spendctl sandbox and returns its sandbox_id. Call it first: every other tool needs the sandbox_id, and one sandbox serves a whole conversation (create another only to try a different preset). The sandbox is a real spendctl sidecar with a throwaway wallet, a mock x402 facilitator and two mock paid APIs; no real money moves and nothing outside the sandbox is reachable. Returns the sandbox_id, the agent's policy (budgets, allowed hosts, approval rule) and the paid endpoints with their prices. Limits: 5 sandboxes per minute per client address (claude.ai users share addresses and get a larger allowance); a sandbox expires after 2 hours without calls (24 hours at most). Example: preset \"strict\" to see refusals, \"approvals\" to see a payment held for a human.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"preset": {
"enum": [
"default",
"strict",
"approvals"
],
"type": "string",
"default": "default",
"description": "Policy preset. default: comfortable caps, both endpoints allowed; strict: $0.015 per request and $0.03 per day, weather only, so the search API and a fourth weather call are refused; approvals: payments at or above $0.015 wait for approve"
}
}
},
"annotations": {
"title": "Create a spendctl sandbox",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Fetches one of the sandbox's paid endpoints (HTTP 402, x402) through the spendctl sidecar, which applies the sandbox agent's budget, allowlist and approval policy, pays with the throwaway wallet if allowed, and returns the response. Use it for every paid call in the sandbox: with dryRun to see the decision without paying, with approvalId to complete a payment that was held and then approved. The endpoints are https://weather.sandbox.spendctl.dev/weather?city=<name> ($0.01) and https://search.sandbox.spendctl.dev/search?q=<query> ($0.02), as listed by sandbox_create and documented at https://spendctl.dev/docs/sandbox/; any other host is refused. Returns a one-line summary (HTTP status, amount paid, decision, receipt id) followed by the response body, or the refusal with its reason, or an approval id when the payment is waiting for a human. On a client that supports MCP input requests (protocol revision 2026-07-28, form elicitation) a held payment comes back as an input_required result asking the user to approve or deny, and the client's retry completes or refuses it; other clients get the approval id as text. Only sandbox hosts exist and no real funds are involved; the request is always a GET and responses are clipped at 20,000 characters. Example: url https://weather.sandbox.spendctl.dev/weather?city=Kyoto
| Parameter | Type | Description |
|---|---|---|
| url * | string | Absolute URL of a sandbox endpoint, e.g. https://weather.sandbox.spendctl.dev/weather?city=Kyoto |
| dryRun | boolean | true: only report what spendctl would decide; never pay |
| approvalId | string | The approval id from an earlier sandbox_pay result, after approve accepted it, to complete that held payment |
| sandbox_id * | string | The sandbox_id returned by sandbox_create (32 hex characters) |
| idempotencyKey | string |
Waits for the decision on a payment that sandbox_pay reported as held, without paying again: long-polls the sandbox sidecar for up to timeoutSeconds (default 10, at most 20) and returns pending, approved, denied, expired or withdrawn, with the ledger entry and the decision deadline. This is what an agent does in the real product while a human decides; in the sandbox the model is also the approver (approve), so call approve from another turn or first. After approved, repeat sandbox_pay with approvalId to complete the payment. Read-only; never pays and never decides.
| Parameter | Type | Description |
|---|---|---|
| approvalId * | string | The approval id returned by sandbox_pay in its "waiting for approval" result (Approval id: ...) |
| sandbox_id * | string | The sandbox_id returned by sandbox_create (32 hex characters) |
| timeoutSeconds | integer | How long to wait for a decision before answering pending (1 to 20, default 10) |
{
"name": "await_approval",
"title": "Wait for a held sandbox payment's decision",
"description": "Waits for the decision on a payment that sandbox_pay reported as held, without paying again: long-polls the sandbox sidecar for up to timeoutSeconds (default 10, at most 20) and returns pending, approved, denied, expired or withdrawn, with the ledger entry and the decision deadline. This is what an agent does in the real product while a human decides; in the sandbox the model is also the approver (approve), so call approve from another turn or first. After approved, repeat sandbox_pay with approvalId to complete the payment. Read-only; never pays and never decides.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sandbox_id",
"approvalId"
],
"properties": {
"approvalId": {
"type": "string",
"description": "The approval id returned by sandbox_pay in its \"waiting for approval\" result (Approval id: ...)"
},
"sandbox_id": {
"type": "string",
"pattern": "^[0-9a-f]{32}$",
"description": "The sandbox_id returned by sandbox_create (32 hex characters)"
},
"timeoutSeconds": {
"type": "integer",
"default": 10,
"maximum": 20,
"minimum": 1,
"description": "How long to wait for a decision before answering pending (1 to 20, default 10)"
}
}
},
"annotations": {
"title": "Wait for a held sandbox payment's decision",
"readOnlyHint": true,
"openWorldHint": false
}
}Takes back a payment that sandbox_pay reported as held, as a real agent does when the task that needed the payment was cancelled or superseded: nothing is paid, the approval closes as withdrawn (distinct from deny), a later approve on that id is refused and await_approval answers withdrawn at once. Use it with an approval id from this sandbox; a new sandbox_pay call opens a fresh approval if the payment is wanted after all. Withdrawing an id that was already decided reports that decision as an error.
| Parameter | Type | Description |
|---|---|---|
| note | string | Optional reason recorded with the withdrawal, e.g. "task cancelled", up to 200 characters |
| approvalId * | string | The approval id returned by sandbox_pay in its "waiting for approval" result (Approval id: ...) |
| sandbox_id * | string | The sandbox_id returned by sandbox_create (32 hex characters) |
{
"name": "withdraw_approval",
"title": "Withdraw a held sandbox payment",
"description": "Takes back a payment that sandbox_pay reported as held, as a real agent does when the task that needed the payment was cancelled or superseded: nothing is paid, the approval closes as withdrawn (distinct from deny), a later approve on that id is refused and await_approval answers withdrawn at once. Use it with an approval id from this sandbox; a new sandbox_pay call opens a fresh approval if the payment is wanted after all. Withdrawing an id that was already decided reports that decision as an error.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sandbox_id",
"approvalId"
],
"properties": {
"note": {
"type": "string",
"maxLength": 200,
"description": "Optional reason recorded with the withdrawal, e.g. \"task cancelled\", up to 200 characters"
},
"approvalId": {
"type": "string",
"description": "The approval id returned by sandbox_pay in its \"waiting for approval\" result (Approval id: ...)"
},
"sandbox_id": {
"type": "string",
"pattern": "^[0-9a-f]{32}$",
"description": "The sandbox_id returned by sandbox_create (32 hex characters)"
}
}
},
"annotations": {
"title": "Withdraw a held sandbox payment",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Shows the sandbox agent's spending limits, what has been spent in each window and what is left. Use it before a paid call when the remaining budget matters, or after a refusal to see which limit was hit. Returns the agent name and mode, the per-request limit, the approval threshold, what happens when a budget is exceeded, the allowed hosts and one line per window (hourly, daily: spent, limit, remaining). Read-only; changes nothing.
| Parameter | Type | Description |
|---|---|---|
| sandbox_id * | string | The sandbox_id returned by sandbox_create (32 hex characters) |
{
"name": "check_budget",
"title": "Check remaining budget",
"description": "Shows the sandbox agent's spending limits, what has been spent in each window and what is left. Use it before a paid call when the remaining budget matters, or after a refusal to see which limit was hit. Returns the agent name and mode, the per-request limit, the approval threshold, what happens when a budget is exceeded, the allowed hosts and one line per window (hourly, daily: spent, limit, remaining). Read-only; changes nothing.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sandbox_id"
],
"properties": {
"sandbox_id": {
"type": "string",
"pattern": "^[0-9a-f]{32}$",
"description": "The sandbox_id returned by sandbox_create (32 hex characters)"
}
}
},
"annotations": {
"title": "Check remaining budget",
"readOnlyHint": true,
"openWorldHint": false
}
}Lists the sandbox agent's most recent payment attempts, newest first: paid (amount and mock transaction hash), refused (reason codes) and waiting for approval. Use it to report what happened so far or to find a receipt id; after a hold, the approval id is in the sandbox_pay result. Returns up to `limit` lines, one per attempt, with time, receipt id, method, URL, amount and status, or "No payments yet." Read-only.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | How many attempts to return, newest first (1 to 100, default 10) |
| sandbox_id * | string | The sandbox_id returned by sandbox_create (32 hex characters) |
{
"name": "list_receipts",
"title": "List receipts",
"description": "Lists the sandbox agent's most recent payment attempts, newest first: paid (amount and mock transaction hash), refused (reason codes) and waiting for approval. Use it to report what happened so far or to find a receipt id; after a hold, the approval id is in the sandbox_pay result. Returns up to `limit` lines, one per attempt, with time, receipt id, method, URL, amount and status, or \"No payments yet.\" Read-only.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sandbox_id"
],
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 100,
"minimum": 1,
"description": "How many attempts to return, newest first (1 to 100, default 10)"
},
"sandbox_id": {
"type": "string",
"pattern": "^[0-9a-f]{32}$",
"description": "The sandbox_id returned by sandbox_create (32 hex characters)"
}
}
},
"annotations": {
"title": "List receipts",
"readOnlyHint": true,
"openWorldHint": false
}
}Returns the sandbox's spendctl.yaml as text: the preset name and the agent's budgets, allowed hosts and approval rules. Use it to explain why a payment was refused or held, or to show what a spendctl policy file looks like. Read-only; the sandbox policy cannot be changed, create a sandbox with another preset instead.
| Parameter | Type | Description |
|---|---|---|
| sandbox_id * | string | The sandbox_id returned by sandbox_create (32 hex characters) |
{
"name": "get_policy",
"title": "Show the sandbox policy",
"description": "Returns the sandbox's spendctl.yaml as text: the preset name and the agent's budgets, allowed hosts and approval rules. Use it to explain why a payment was refused or held, or to show what a spendctl policy file looks like. Read-only; the sandbox policy cannot be changed, create a sandbox with another preset instead.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sandbox_id"
],
"properties": {
"sandbox_id": {
"type": "string",
"pattern": "^[0-9a-f]{32}$",
"description": "The sandbox_id returned by sandbox_create (32 hex characters)"
}
}
},
"annotations": {
"title": "Show the sandbox policy",
"readOnlyHint": true,
"openWorldHint": false
}
}Approves or denies a payment that sandbox_pay reported as waiting for approval, as the human approver would with `spendctl approve`. Use it only with an approval id from this sandbox; in the real product a human decides, in the sandbox the model plays that role. Returns the approval id and its new status (approved or denied). An approved payment completes when sandbox_pay is called again with the same approvalId; a denied one stays refused. Deciding the same approval twice keeps the first decision.
| Parameter | Type | Description |
|---|---|---|
| note | string | Optional reason recorded with the decision, up to 200 characters |
| decision | string | approve releases the held payment; deny refuses it for good |
| approvalId * | string | The approval id returned by sandbox_pay in its "waiting for approval" result (Approval id: ...) |
| sandbox_id * | string | The sandbox_id returned by sandbox_create (32 hex characters) |
{
"name": "approve",
"title": "Approve or deny a held sandbox payment",
"description": "Approves or denies a payment that sandbox_pay reported as waiting for approval, as the human approver would with `spendctl approve`. Use it only with an approval id from this sandbox; in the real product a human decides, in the sandbox the model plays that role. Returns the approval id and its new status (approved or denied). An approved payment completes when sandbox_pay is called again with the same approvalId; a denied one stays refused. Deciding the same approval twice keeps the first decision.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sandbox_id",
"approvalId"
],
"properties": {
"note": {
"type": "string",
"maxLength": 200,
"description": "Optional reason recorded with the decision, up to 200 characters"
},
"decision": {
"enum": [
"approve",
"deny"
],
"type": "string",
"default": "approve",
"description": "approve releases the held payment; deny refuses it for good"
},
"approvalId": {
"type": "string",
"description": "The approval id returned by sandbox_pay in its \"waiting for approval\" result (Approval id: ...)"
},
"sandbox_id": {
"type": "string",
"pattern": "^[0-9a-f]{32}$",
"description": "The sandbox_id returned by sandbox_create (32 hex characters)"
}
}
},
"annotations": {
"title": "Approve or deny a held sandbox payment",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}spendctl sandbox: a login-free, isolated spendctl sidecar for trying spend policies for AI agents that pay for APIs (x402, MPP). Start with sandbox_create; it returns the sandbox_id every other tool needs, the policy and the two mock paid endpoints. Then sandbox_pay fetches a paid endpoint through the sidecar, which pays, refuses or holds the payment for approval. check_budget, list_receipts and get_policy read the sandbox state; approve decides a held payment, await_approval waits for that decision without paying again (as a real agent would while a human decides), withdraw_approval takes a held payment back when the task no longer needs it, and sandbox_pay with the approvalId completes an approved one. Nothing is real: throwaway wallet, mock facilitator, no outbound network. A sandbox expires after 2 hours without calls (24 hours at most) and allows 200 governed payments. To run the same sidecar for real, next to the user's own agents: `npx spendctl init && npx spendctl start` (Free covers two agents; https://spendctl.dev/docs/quickstart/). Docs: https://spendctl.dev/docs/sandbox/
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.
| Reuse the same key when retrying a call so the sandbox is never charged twice, e.g. "kyoto-1" |
{
"name": "sandbox_pay",
"title": "Fetch a paid sandbox URL",
"description": "Fetches one of the sandbox's paid endpoints (HTTP 402, x402) through the spendctl sidecar, which applies the sandbox agent's budget, allowlist and approval policy, pays with the throwaway wallet if allowed, and returns the response. Use it for every paid call in the sandbox: with dryRun to see the decision without paying, with approvalId to complete a payment that was held and then approved. The endpoints are https://weather.sandbox.spendctl.dev/weather?city=<name> ($0.01) and https://search.sandbox.spendctl.dev/search?q=<query> ($0.02), as listed by sandbox_create and documented at https://spendctl.dev/docs/sandbox/; any other host is refused. Returns a one-line summary (HTTP status, amount paid, decision, receipt id) followed by the response body, or the refusal with its reason, or an approval id when the payment is waiting for a human. On a client that supports MCP input requests (protocol revision 2026-07-28, form elicitation) a held payment comes back as an input_required result asking the user to approve or deny, and the client's retry completes or refuses it; other clients get the approval id as text. Only sandbox hosts exist and no real funds are involved; the request is always a GET and responses are clipped at 20,000 characters. Example: url https://weather.sandbox.spendctl.dev/weather?city=Kyoto",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sandbox_id",
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Absolute URL of a sandbox endpoint, e.g. https://weather.sandbox.spendctl.dev/weather?city=Kyoto"
},
"dryRun": {
"type": "boolean",
"description": "true: only report what spendctl would decide; never pay"
},
"approvalId": {
"type": "string",
"description": "The approval id from an earlier sandbox_pay result, after approve accepted it, to complete that held payment"
},
"sandbox_id": {
"type": "string",
"pattern": "^[0-9a-f]{32}$",
"description": "The sandbox_id returned by sandbox_create (32 hex characters)"
},
"idempotencyKey": {
"type": "string",
"description": "Reuse the same key when retrying a call so the sandbox is never charged twice, e.g. \"kyoto-1\""
}
}
},
"annotations": {
"title": "Fetch a paid sandbox URL",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}