AnyAPI

Run an API

run_api

Destructive

Execute an API by SKU with a normalized input payload. Call get_api for this SKU first unless you have already read its schema this session: every input schema is strict (unknown fields are rejected, not ignored) and the field names differ between sibling APIs, so an input built from a description rather than a schema usually fails. Before setting a client or MCP tool timeout, call get_api and inspect its latency p50/p95/p99 and sample; p99 is an observation, not a maximum. Requires a valid AnyAPI key as a Bearer token. Charges the USD wallet only on success. Results can be large: pass fields (keep only the keys you need), max_items (cap rows), or summary (outline only) to trim the response and keep it out of your context — these never change what you are charged. Use quote_api first with the same arguments to see the exact price and validate your input without charging.

Input Schema

TableJSON Schema

Name	Required	Description
`jq`	No	optional: a jq expression to reshape the result; its output replaces 'output' (multiple outputs collect into an array). Example: '.data \| {title, description, md: .markdown[:3500]}'. Sandboxed 250ms/2MB budget; on failure the full result is returned with jqError. Does not change cost
`input`	Yes	normalized input payload matching the API input schema
`fields`	No	optional: keep only these keys on each result item (dotted paths like 'author.name' descend into nested objects). Shrinks the response without changing cost
`sku_id`	Yes	the API SKU slug to execute
`context`	Yes	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."
`summary`	No	optional: return only a structural outline (top-level keys, item counts, and per-field byte sizes) instead of the full data. Does not change cost
`max_items`	No	optional: cap the number of result items returned; a _truncated note reports how many were withheld. Does not change cost

Output Schema

TableJSON Schema

Name	Required	Description
`hint`	No	optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireFields ["nextCursor"] (may cost more per request) if you need the full list
`error`	No	safe AnyAPI failure code when durable work failed
`items`	Yes	number of result rows returned. For per-result SKUs the per-item cost is charged against this; for input-priced SKUs (perItemUnit != result) the charge is per submitted input, independent of this count
`output`	Yes	normalized output payload
`source`	No	the source that served this run: pass its id back in 'source' to prefer it again, or in 'ignoreSources' to avoid it. Absent when no source identity applies
`status`	No	durable request status: queued, running, succeeded, failed, or expired
`costUsd`	Yes	amount charged to the wallet in USD
`jqError`	No	present only when a jq expression failed; output then holds the full unshaped result and this explains why the reshape did not apply
`provider`	Yes	the provider serving the request (AnyAPI)
`replayed`	Yes	true when this response replays an identical earlier call (same API, same input) from the last few minutes instead of running again: nothing new was executed and costUsd restates the original charge, it was NOT charged a second time
`resultId`	No	opaque handle to the full result, cached ~15 min; pass it to read_result to dig deeper for free (no re-run, no charge). Absent when the result was too large to cache
`requestId`	No	durable request identifier; pass it to get_request to resume without repeating the paid POST
`nextAction`	No	machine-actionable resume instruction present while durable work is pending
`serviceOutcome`	No	end-to-end AnyAPI service outcome when known
`settlementState`	No	payment settlement state when known; independent of durable request status

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 16, 2026

addedOutput schema / properties / source

Added value: +{
+  "additionalProperties": false,
+  "description": "the source that served this run: pass its id back in 'source' to prefer it again, or in 'ignoreSources' to avoid it. Absent when no source identity applies",
+  "properties": {
+    "artworkKey": {
+      "type": "string"
+    },
+    "id": {
+      "type": "string"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "name": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "id",
+    "name",
+    "kind",
+    "artworkKey"
+  ],
+  "type": [
+    "null",
+    "object"
+  ]
+}

Changed1 schema field changedSep 13, 2026

changedOutput schema / properties / hint / description

Previous value: -"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireCursor true (may cost more per request) if you need the full list"New value: +"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireFields [\"nextCursor\"] (may cost more per request) if you need the full list"

Changed12 schema fields changedSep 3, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / context

Added value: +{
+  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "sku_id",
-  "input"
-]New value: +[
+  "sku_id",
+  "input",
+  "context"
+]

addedOutput schema / properties / error

Added value: +{
+  "additionalProperties": false,
+  "description": "safe AnyAPI failure code when durable work failed",
+  "properties": {
+    "code": {
+      "description": "safe AnyAPI error code",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code"
+  ],
+  "type": [
+    "null",
+    "object"
+  ]
+}

changedOutput schema / properties / hint / description

Previous value: -"optional nudge, present only on large untrimmed results, suggesting fields/max_items/summary to keep future responses out of your context"New value: +"optional nudge. 'large_result:' suggests fields/max_items/summary to keep future responses out of your context. 'paging_unavailable:' means this result came from a source that cannot return a nextCursor, so it may be INCOMPLETE and you cannot page further - re-run with requireCursor true (may cost more per request) if you need the full list"

addedOutput schema / properties / nextAction

Added value: +{
+  "additionalProperties": false,
+  "description": "machine-actionable resume instruction present while durable work is pending",
+  "properties": {
+    "requestId": {
+      "description": "request_id argument for the next tool call",
+      "type": "string"
+    },
+    "retryAfterSeconds": {
+      "description": "minimum delay before polling again",
+      "type": "integer"
+    },
+    "tool": {
+      "description": "MCP tool to call next",
+      "type": "string"
+    }
+  },
+  "required": [
+    "tool",
+    "requestId",
+    "retryAfterSeconds"
+  ],
+  "type": [
+    "null",
+    "object"
+  ]
+}

addedOutput schema / properties / replayed

Added value: +{
+  "description": "true when this response replays an identical earlier call (same API, same input) from the last few minutes instead of running again: nothing new was executed and costUsd restates the original charge, it was NOT charged a second time",
+  "type": "boolean"
+}

addedOutput schema / properties / requestId

Added value: +{
+  "description": "durable request identifier; pass it to get_request to resume without repeating the paid POST",
+  "type": "string"
+}

addedOutput schema / properties / serviceOutcome

Added value: +{
+  "description": "end-to-end AnyAPI service outcome when known",
+  "type": "string"
+}

addedOutput schema / properties / settlementState

Added value: +{
+  "description": "payment settlement state when known; independent of durable request status",
+  "type": "string"
+}

addedOutput schema / properties / status

Added value: +{
+  "description": "durable request status: queued, running, succeeded, failed, or expired",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "output",
-  "provider",
-  "costUsd",
-  "items"
-]New value: +[
+  "output",
+  "provider",
+  "costUsd",
+  "items",
+  "replayed"
+]

Changed4 schema fields changedJul 10, 2026

addedInput schema / properties / jq

Added value: +{
+  "description": "optional: a jq expression to reshape the result; its output replaces 'output' (multiple outputs collect into an array). Example: '.data | {title, description, md: .markdown[:3500]}'. Sandboxed 250ms/2MB budget; on failure the full result is returned with jqError. Does not change cost",
+  "type": "string"
+}

changedInput schema / properties / summary / description

Previous value: -"optional: return only a structural outline (top-level keys and item counts) instead of the full data. Does not change cost"New value: +"optional: return only a structural outline (top-level keys, item counts, and per-field byte sizes) instead of the full data. Does not change cost"

addedOutput schema / properties / jqError

Added value: +{
+  "description": "present only when a jq expression failed; output then holds the full unshaped result and this explains why the reshape did not apply",
+  "type": "string"
+}

addedOutput schema / properties / resultId

Added value: +{
+  "description": "opaque handle to the full result, cached ~15 min; pass it to read_result to dig deeper for free (no re-run, no charge). Absent when the result was too large to cache",
+  "type": "string"
+}

First observedJun 18, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (which already mark it as non-read-only and potentially destructive), the description discloses strict schema rejection, charging only on success, response-size context risks, and the semantic of p99 as an observation rather than a maximum. These are meaningful behavioral traits not present in annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long (six sentences) but every sentence carries operational information: prerequisite schema lookup, strictness warning, timeout guidance, auth, billing, and response trimming. It is front-loaded with the core purpose, though slightly dense; a small amount could be trimmed without losing value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter tool with a rich output schema, the description covers prerequisites, schema strictness, authentication, cost implications, timeout considerations, and response-size mitigation. The presence of an output schema means return-value details are not the description's job; nothing an agent needs to invoke correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes all 7 parameters at 100% coverage, so the baseline is 3. The description adds important semantics: inputs must be built from the schema because strict validation rejects unknown fields, and the response-trimming parameters (fields, max_items, summary) never affect cost. This exceeds the baseline but is somewhat redundant with the schema's per-parameter cost notes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Execute an API by SKU with a normalized input payload.' This clearly distinguishes run_api from siblings like get_api (schema retrieval), quote_api (pricing), and list_apis (discovery), leaving no ambiguity about what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: call get_api first unless the schema is already read, and use quote_api first to see price and validate input without charging. It also directs the agent to inspect latency via get_api before setting timeouts. No rival tool context is left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All AnyAPI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.