FastAPI MCP Server + LangChain Client Example
by SDCalvo
This project demonstrates how to expose FastAPI endpoints as Model Context Protocol (MCP) tools using `fastapi-mcp`. It includes a basic LangChain agent that connects to the FastAPI server via HTTP/SSE to discover and use the exposed tools.
Last updated: N/A
What is FastAPI MCP Server + LangChain Client Example?
This is an example project showcasing how to build a FastAPI server with MCP capabilities, allowing it to be used as a tool by MCP clients like the Cursor editor's agent. It also includes a LangChain client that connects to the server and uses the exposed tools.
How to use FastAPI MCP Server + LangChain Client Example?
To use this server, first clone the repository and install the necessary dependencies using uv. Then, create a .env file with your OpenAI API key. Run the FastAPI MCP server using uvicorn main:app --reload --port 8000 and the LangChain client using uv run python langchain_client.py. Optionally, test the server with the MCP Inspector.
Key features of FastAPI MCP Server + LangChain Client Example
Exposes FastAPI endpoints as MCP tools
Includes a LangChain agent client for tool discovery and usage
Supports HTTP/SSE communication
Provides a
.cursor/mcp.jsonconfiguration for Cursor integration
Use cases of FastAPI MCP Server + LangChain Client Example
Integrating FastAPI applications with MCP-compatible clients
Building AI agents that can leverage FastAPI endpoints as tools
Testing and experimenting with the Model Context Protocol
Connecting Cursor editor with local APIs
FAQ from FastAPI MCP Server + LangChain Client Example
What is Model Context Protocol (MCP)?
What is Model Context Protocol (MCP)?
MCP is a protocol that allows applications to expose their functionality as tools that can be used by other applications, such as AI agents.
What is fastapi-mcp?
What is fastapi-mcp?
fastapi-mcp is a library that simplifies the process of exposing FastAPI endpoints as MCP tools.
How do I install the dependencies for this project?
How do I install the dependencies for this project?
Use the uv pip install command as described in the README to install all required packages.
How do I configure Cursor to use this server?
How do I configure Cursor to use this server?
Create a .cursor/mcp.json file with the server URL and enable the server in Cursor's settings.
How do I test the server?
How do I test the server?
You can use the MCP Inspector tool or the provided LangChain client to test the server's functionality.