What is the purpose of this project?
It serves as a learning example showing how to mount a Model Context Protocol server on top of a FastAPI application, with a matching client that communicates using the MCP client library.
@KimiJL
基本信息
Example web app mounting a model context protocol (MCP) server on a FastAPI server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"fastapi-mcp": {
"command": "docker",
"args": [
"build",
"-t",
"fastapi-mcp",
"."
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Description is a simple example web app and client that demonstrates mounting a Model Context Protocol (MCP) server onto an existing FastAPI server. It is intended for developers learning how to integrate MCP with FastAPI.
Build and run the server using Docker (docker build -t fastapi-mcp . then docker run -p 8000:8000 --net=host fastapi-mcp) or set up a Python environment, install dependencies, and run uvicorn src.main:app. Then execute the sample client with python client/client.py.
It serves as a learning example showing how to mount a Model Context Protocol server on top of a FastAPI application, with a matching client that communicates using the MCP client library.
The server can run inside Docker or directly with Python. The client requires the packages listed in `requirements.txt`.
The MCP server is mounted as a sub‑application on the FastAPI server, currently limited to the root path `/` due to a known issue in the MCP Python SDK.

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
评论