API Docs

You can crawl API documentation sites and expose their content through the Model Context Protocol, enabling AI models to search, browse, and reference API specifications efficiently. This MCP server fetches, stores, and serves API docs as structured resources for quick access and integration with AI workflows.

How to use

Start by choosing how you want to run or connect to the MCP server. You can run it locally on your machine and connect with any MCP client, or connect to a remote server URL if one is provided by your team.

To run the server locally, use the standard start command and then connect via an MCP client by pointing it to the server URL you started. The server will expose API endpoint specifications, data models, and code snippets as MCP resources for easy discovery.

Once the server is running, use the client configuration to integrate with your favorite MCP client. The client should be configured to execute the server command so it can fetch and interact with the API docs as needed.

How to install

Prerequisites: you need Python and a virtual environment tool available on your system.

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install the package in editable mode
pip install -e .

Additional sections

Configuration and usage details focus on how to start and connect the server, along with the MCP capabilities and available tools.

Key capabilities include crawling API documentation sites, exposing docs as MCP resources, providing search tools for endpoints, and offering prompt templates and offline data storage for API specs.

Environment and tools are designed to help you discover, compare, and generate code against API endpoints, with dedicated tools for searching endpoints, listing them, retrieving details, and finding usage examples.

Notes

If you need to connect to a remote MCP server URL, configure your client with the server URL and ensure the server is accessible from your network.

Available tools

search_api

Search for API endpoints by name, path, or description

get_endpoint_details

Get detailed information about a specific endpoint

list_endpoints

List all available API endpoints

find_examples

Find examples for a specific API endpoint