AnyAPI MCP Server

anyapi-mcp-server

If it has an API, you can MCP it.

Traditional MCP servers hand-pick a handful of endpoints and call it a day — locking you into whatever subset someone decided was "enough." Why settle for a fraction of an API when you can have all of it?

anyapi-mcp-server is a universal MCP server that connects any REST API to AI assistants like Claude, Cursor, and other LLM-powered tools — just point it at an OpenAPI spec or Postman collection. Every endpoint the API provides becomes available instantly, with GraphQL-style field selection and automatic schema inference. No custom server code, no artificial limits.

Quick start

1. Install

npm install -g anyapi-mcp-server

2. Add to your MCP client (Cursor, Claude Desktop, etc.)

{
  "mcpServers": {
    "your-api": {
      "command": "npx",
      "args": [
        "-y",
        "anyapi-mcp-server",
        "--name", "your-api",
        "--spec", "path/to/openapi.json",
        "--base-url", "https://api.example.com",
        "--header", "Authorization: Bearer ${API_KEY}"
      ],
      "env": {
        "API_KEY": "your-api-key"
      }
    }
  }
}

3. Use the tools — discover endpoints with list_api, inspect schemas with call_api, fetch data with query_api.

Provider examples

Ready-to-use configurations for popular APIs:

These work with any API that has an OpenAPI or Postman spec — the above are just examples. Stripe, Twilio, Shopify, HubSpot, and anything else with a REST API will work the same way.

CLI reference

Required flags

Optional flags

OAuth flags

For APIs that use OAuth 2.0 instead of static tokens. If any of the three required flags is provided, all three are required. All flags support ${ENV_VAR}.

See the Google Workspace guide for a complete OAuth example.

Tools

The server exposes four tools (plus auth when OAuth is configured):

`list_api` — Browse endpoints

Discover what the API offers. Call with no arguments to see all categories, provide category to list endpoints in a tag, or search to find endpoints by keyword.

`call_api` — Inspect an endpoint

Makes a real HTTP request and returns the inferred GraphQL schema (SDL) — not the data itself. Use this to discover the response shape and get suggestedQueries you can copy into query_api. Also returns per-field token costs (fieldTokenCosts) and a dataKey for cache reuse. For PUT/PATCH requests, automatically creates a pre-write backup (returns backupDataKey). Supports bodyFile for large payloads and blocks requests with detected placeholder values.

`query_api` — Fetch data

Fetches data and returns only the fields you select via a GraphQL query. Supports both reads and writes (mutations for POST/PUT/DELETE/PATCH). Pass a dataKey from call_api to reuse cached data with zero HTTP calls.

# Read
{ items { id name status } _count }

# Write
mutation { post_endpoint(input: { name: "example" }) { id } }

Key parameters:

• maxTokens — token budget for the response (default 4000). Arrays are truncated to fit.
• dataKey — reuse cached data from a previous call_api or query_api response.
• jsonFilter — d