A zero-configuration tool for automatically exposing FastAPI endpoints as Model Context Protocol (MCP) tools.
- Direct integration - Mount an MCP server directly to your FastAPI app
- Zero configuration required - just point it at your FastAPI app and it works
- Automatic discovery of all FastAPI endpoints and conversion to MCP tools
- Preserving schemas of your request models and response models
- Preserve documentation of all your endpoints, just as it is in Swagger
- Extend - Add custom MCP tools alongside the auto-generated ones
We recommend using uv, a fast Python package installer:
uv add fastapi-mcp
Alternatively, you can install with pip:
pip install fastapi-mcp
The simplest way to use FastAPI-MCP is to add an MCP server directly to your FastAPI application:
from fastapi import FastAPI
from fastapi_mcp import add_mcp_server
# Your FastAPI app
app = FastAPI()
# Mount the MCP server to your app
add_mcp_server(
app, # Your FastAPI app
mount_path="/mcp", # Where to mount the MCP server
name="My API MCP", # Name for the MCP server
)
That's it! Your auto-generated MCP server is now available at https://app.base.url/mcp
.
FastAPI-MCP provides several ways to customize and control how your MCP server is created and configured. Here are some advanced usage patterns:
from fastapi import FastAPI
from fastapi_mcp import add_mcp_server
app = FastAPI()
mcp_server = add_mcp_server(
app, # Your FastAPI app
mount_path="/mcp", # Where to mount the MCP server
name="My API MCP", # Name for the MCP server
describe_all_responses=True, # False by default. Include all possible response schemas in tool descriptions, instead of just the successful response.
describe_full_response_schema=True # False by default. Include full JSON schema in tool descriptions, instead of just an LLM-friendly response example.
)
# Optionally add custom tools in addition to existing APIs.
@mcp_server.tool()
async def get_server_time() -> str:
"""Get the current server time."""
from datetime import datetime
return datetime.now().isoformat()
See the examples directory for complete examples.
Once your FastAPI app with MCP integration is running, you can connect to it with any MCP client supporting SSE, such as Cursor:
-
Run your application.
-
In Cursor -> Settings -> MCP, use the URL of your MCP server endpoint (e.g.,
http://localhost:8000/mcp
) as sse. -
Cursor will discover all available tools and resources automatically.
Connecting to the MCP Server using mcp-proxy stdio
If your MCP client does not support SSE, for example Claude Desktop:
-
Run your application.
-
Install mcp-proxy, for example:
uv tool install mcp-proxy
. -
Add in Claude Desktop MCP config file (
claude_desktop_config.json
):
On Windows:
{
"mcpServers": {
"my-api-mcp-proxy": {
"command": "mcp-proxy",
"args": ["http://127.0.0.1:8000/mcp"]
}
}
}
On MacOS:
{
"mcpServers": {
"my-api-mcp-proxy": {
"command": "/Full/Path/To/Your/Executable/mcp-proxy",
"args": ["http://127.0.0.1:8000/mcp"]
}
}
}
Find the path to mcp-proxy by running in Terminal: which mcp-proxy
.
- Claude Desktop will discover all available tools and resources automatically
If you're interested in contributing to FastAPI-MCP:
# Clone the repository
git clone https://github.com/tadata-org/fastapi_mcp.git
cd fastapi_mcp
# Create a virtual environment and install dependencies with uv
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv add -e ".[dev]"
# Run tests
uv run pytest
For more details about contributing, see CONTRIBUTING.md.
Join MCParty Slack community to connect with other MCP enthusiasts, ask questions, and share your experiences with FastAPI-MCP.
- Python 3.10+
- uv
MIT License. Copyright (c) 2024 Tadata Inc.
Developed and maintained by Tadata Inc.