FastAPI MCP Server
A Model Context Protocol server that provides tools for introspecting and analyzing FastAPI applications, including route discovery, model schema extraction, and source code viewing. It enables users to explore API structures, generate documentation, and debug dependency injection hierarchies through natural language.
README
FastAPI MCP Server
A Model Context Protocol (MCP) server that provides comprehensive tools for introspecting and working with FastAPI applications.
Features
๐ง Tools
- load_fastapi_app - Load a FastAPI application from a module path
- list_routes - List all routes with optional filtering
- get_route_details - Get comprehensive details about a specific route
- get_openapi_schema - Extract the OpenAPI schema
- list_models - List all Pydantic models used in the app
- get_model_schema - Get detailed schema for a specific model
- search_routes - Search routes by query and criteria
- analyze_dependencies - Analyze dependency injection usage
- get_route_source - View the source code of route handlers
Installation
pip install -e .
Usage
With Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"fastapi": {
"command": "python",
"args": [
"-m",
"fastapi_mcp_server.server"
],
"cwd": "/path/to/your/fastapi/project"
}
}
}
Standalone
# From your FastAPI project directory
python -m fastapi_mcp_server.server
Example Usage
1. Load Your FastAPI App
Tool: load_fastapi_app
Arguments: {"app_path": "main:app"}
2. List All Routes
Tool: list_routes
Arguments: {}
Or with filters:
Tool: list_routes
Arguments: {
"method_filter": "GET",
"tag_filter": "users"
}
3. Get Route Details
Tool: get_route_details
Arguments: {
"path": "/users/{user_id}",
"method": "GET"
}
4. Search for Routes
Tool: search_routes
Arguments: {
"query": "authentication",
"has_auth": true
}
5. View Route Source Code
Tool: get_route_source
Arguments: {
"path": "/users",
"method": "POST"
}
6. List All Models
Tool: list_models
Arguments: {}
7. Get Model Schema
Tool: get_model_schema
Arguments: {"model_name": "User"}
8. Get OpenAPI Schema
Tool: get_openapi_schema
Arguments: {}
Or for specific paths:
Tool: get_openapi_schema
Arguments: {
"include_only": ["/users", "/users/{user_id}"]
}
9. Analyze Dependencies
Tool: analyze_dependencies
Arguments: {}
Example FastAPI App
See example_app.py for a sample FastAPI application to test with.
Use Cases
๐ API Discovery
- Quickly understand what endpoints exist
- Find routes by functionality or path
- Explore API structure
๐ Documentation Generation
- Extract OpenAPI schemas
- Get detailed parameter information
- View model schemas with examples
๐ Debugging
- Inspect route configurations
- View dependency injection hierarchy
- Check parameter validations
๐จ Development
- Generate client code from schemas
- Understand existing APIs before modification
- Find all routes using specific models
๐งช Testing
- List all endpoints for test coverage
- Get parameter requirements for test cases
- Validate response models
Requirements
- Python 3.10+
- FastAPI 0.100.0+
- MCP 1.0.0+
- Pydantic 2.0.0+
Contributing
Contributions are welcome! This tool helps developers work more efficiently with FastAPI applications.
License
MIT License - feel free to use in your projects!
Author
Created as part of the FastAPI ecosystem to improve developer experience with AI-assisted development.
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.