About Public Apis Mcp
Public Apis Mcp is an MCP server for searching a catalog of free public APIs drawn from the public-apis GitHub repo. Developers can find APIs by meaning and retrieve full entries by ID.
Key features
- 01Embedding-based API search
- 02Full API details by ID
- 03Catalog and API resources
Use cases
- 01Finding APIs for a development task
- 02Reviewing an API entry by ID
MCP support
Exposes search_public_apis and get_public_api_details tools, plus catalog and per-API resources to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
2Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | |
| query | string | Yes |
Details
From the project READMEPublic APIs MCP
Catalog of free public APIs with semantic search.
The catalog includes an extensive list of APIs from the public-apis GitHub repo.
Thank you to all the maintainers, contributors and API creators! 💯
🎯 Features
search_public_apis: embedding-based search over API names and descriptionsget_public_api_details: retrieve full details byid- Resources:
public-apis://apis,public-apis://api/{id}
🔧 Setup (uv)
Add to MCP clients (e.g., Claude Desktop) using uv.
Claude Desktop
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"public-apis": {
"command": "uvx",
"args": ["public-apis-mcp"]
}
}
}
🚀 Usage
- Build embeddings index (optional; auto-build on first search):
uvx public-apis-mcp build-index
- Run the MCP server over STDIO:
uvx public-apis-mcp run
📋 Tool Reference
search_public_apis
- Purpose: Semantic search over the catalog
- Parameters:
query(str),limit(int, default 5) - Returns: list of
{ id, name, score, snippet }
Example call payload:
{ "name": "search_public_apis", "arguments": { "query": "weather", "limit": 5 } }
get_public_api_details
- Purpose: Fetch full details by
id - Parameters:
id(str) - Returns:
ApiItem
Example call payload:
{ "name": "get_public_api_details", "arguments": { "id": "a6b3a6b3-a6b3-a6b3-a6b3-a6b3a6b3a6b3" } }
🛠️ Development
Prerequisites:
- Python 3.10+
- uv (
https://docs.astral.sh/uv/)
Setup:
uv sync --dev
Run tests:
FREE_APIS_MCP_TEST_MODE=1 uv run pytest -q
Lint and format:
uv run ruff check --fix
uv run ruff format
Type checking:
uv run mypy src/
MCP Client Dev Config
{
"mcpServers": {
"public-apis-dev": {
"command": "uv",
"args": [
"--directory",
"<abs_path>/public-apis-mcp",
"run",
"public-apis-mcp"
]
}
}
}
Build and Try
uv build
uv run --with dist/*.whl public-apis-mcp --help
📦 Data & Index
- Data:
src/public_apis_mcp/datastore/free_apis.json - Embedding index:
src/public_apis_mcp/datastore/index.npz(auto-built)
Testing with MCP Inspector
For exploring and/or developing this server, use the MCP Inspector npm utility:
# Install MCP Inspector
npm install -g @modelcontextprotocol/inspector
# Run local development server with the inspector
npx @modelcontextprotocol/inspector uv run public-apis-mcp
# Run PyPI production server with the inspector
npx @modelcontextprotocol/inspector uvx public-apis-mcp
📝 License
MIT License - see LICENSE file for details.
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.