mcp-public-apis

Give your AI coding agent the ability to find, test, and integrate any of 1,500+ free public APIs — instantly.

Data sourced from the community-maintained public-apis list · synced daily

What is this?

An MCP (Model Context Protocol) server that gives AI coding agents real-time access to the public-apis dataset. Instead of copy-pasting API documentation, your agent can search, probe, and generate working code — all in one conversation.

You:   "Find me a free weather API with no auth that supports HTTPS"
Agent: [calls search_apis] → returns top matches with auth/HTTPS/CORS details

You:   "Test the first one — show me what the response looks like"
Agent: [calls probe_api] → live GET request, returns status + response shape

You:   "Generate an axios snippet for it"
Agent: [calls generate_snippet] → ready-to-paste curl, fetch, and axios code

Installation

Pick the config for your client and paste it in. No build step required — npx handles everything.

File: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
File: %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "public-apis": {
      "command": "npx",
      "args": ["mcp-public-apis"]
    }
  }
}

File: .cursor/mcp.json in your project root (or ~/.cursor/mcp.json globally)

{
  "mcpServers": {
    "public-apis": {
      "command": "npx",
      "args": ["mcp-public-apis"]
    }
  }
}

File: ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "public-apis": {
      "command": "npx",
      "args": ["mcp-public-apis"]
    }
  }
}

Open VS Code → Cline sidebar → MCP Servers tab → Add Server → paste:

{
  "public-apis": {
    "command": "npx",
    "args": ["mcp-public-apis"]
  }
}

git clone https://github.com/josephsenior/pblic-apis-mcp-server
cd pblic-apis-mcp-server
npm install
npm run build
node dist/index.js

Tools

search_apis parameters

How it works

MCP Client (Claude / Cursor / etc.)
        │  JSON-RPC over stdio
        ▼
  mcp-public-apis server
        │
        ├─ In-memory cache (24 h TTL)
        │
        └─ GitHub raw · public-apis/public-apis README.md

1. On first use the server fetches the public-apis README from GitHub, parses every Markdown table row into structured PublicAPI objects, and stores them in a 24-hour in-memory cache.

2. All search and filter operations run locally against that cache — no external call per query.

3. probe_api is the only tool that makes a request to a third-party endpoint (the one you explicitly pass in).

Data source

All API records come from public-apis/public-apis — a community-maintained list of 1,500+ free APIs across 60+ categories. The data is fetched fresh every 24 hours.

License

MIT