FastAPI MCP

Overview

FastAPI MCP is the simplest way to make existing APIs accessible to AI agents. Already have a FastAPI app? Adding MCP support is literally one line of code. Every endpoint automatically becomes an MCP tool that any AI agent can call.

How It Works

1. Install — pip install fastapi-mcp
2. Add one line — mcp = FastApiMCP(app)
3. Mount — mcp.mount()
4. Connect — Your API is now an MCP server

Use Cases

• Internal APIs — Expose company microservices to AI agents
• Legacy systems — Bridge older APIs to MCP
• Prototyping — Quick MCP server from existing code
• SaaS products — Add AI agent support to your product

Getting Started

from fastapi import FastAPI
from fastapi_mcp import FastApiMCP

app = FastAPI()

@app.get("/users/{user_id}")
def get_user(user_id: int):
    return {"id": user_id, "name": "Alice"}

mcp = FastApiMCP(app)
mcp.mount()

Example

After adding FastAPI MCP:
User: "Create an order for 5 widgets"
Agent → POST /orders(product="widget", quantity=5)
Returns: {"order_id": "ORD-456", "product": "widget", "qty": 5}

Alternatives

• FastMCP — Build MCP servers from scratch
• MCP SDK — Low-level MCP implementation
• Composio — Managed API integrations