mcp-public-apis
An MCP server that gives AI coding agents real-time access to the public-apis dataset, enabling search, live probing, and code snippet generation for 1,500+ free public APIs.
README
<div align="center">
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
</div>
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.
<details> <summary><strong>Claude Desktop</strong></summary>
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"]
}
}
}
</details>
<details> <summary><strong>Cursor</strong></summary>
File: .cursor/mcp.json in your project root (or ~/.cursor/mcp.json globally)
{
"mcpServers": {
"public-apis": {
"command": "npx",
"args": ["mcp-public-apis"]
}
}
}
</details>
<details> <summary><strong>Windsurf</strong></summary>
File: ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"public-apis": {
"command": "npx",
"args": ["mcp-public-apis"]
}
}
}
</details>
<details> <summary><strong>Cline (VS Code)</strong></summary>
Open VS Code → Cline sidebar → MCP Servers tab → Add Server → paste:
{
"public-apis": {
"command": "npx",
"args": ["mcp-public-apis"]
}
}
</details>
<details> <summary><strong>Local build</strong></summary>
git clone https://github.com/josephsenior/pblic-apis-mcp-server
cd pblic-apis-mcp-server
npm install
npm run build
node dist/index.js
</details>
Tools
| Tool | What it does | Key parameters |
|---|---|---|
search_apis |
Fuzzy-search 1,500+ APIs by keyword, category, auth type, and HTTPS | query, category, auth, httpsOnly, limit |
get_categories |
List every category with its API count | — |
get_api_detail |
Full record for one API by name | name |
probe_api |
Live HTTP GET to any endpoint — returns status, latency, and response preview | url, apiKey, timeoutMs |
compare_apis |
Side-by-side view of all APIs in a category | category, limit |
find_no_auth_apis |
Only APIs that need zero authentication | category, httpsOnly, limit |
generate_snippet |
Paste-ready curl, fetch, and axios snippets |
url, apiKey, headers |
search_apis parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
query |
string | — | Fuzzy-match against API name and description |
category |
string | — | Exact category name (use get_categories to browse) |
auth |
"No" | "apiKey" | "OAuth" |
— | Filter by auth requirement |
httpsOnly |
boolean | true |
Exclude non-HTTPS APIs |
limit |
number | 5 |
Max results (1–20) |
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
- On first use the server fetches the public-apis README from GitHub, parses every Markdown table row into structured
PublicAPIobjects, and stores them in a 24-hour in-memory cache. - All search and filter operations run locally against that cache — no external call per query.
probe_apiis 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.