Skip to main content
Glama
zongjieshen

Simple FastMCP Server

by zongjieshen

Simple FastMCP Server

This repository contains a minimal MCP server built with FastMCP 2.0. It exposes two tools:

  • add(a: int, b: int) -> int: Returns the sum of two numbers.

  • greet(name: str) -> str: Returns a friendly greeting.

Local Development

Prerequisites:

  • Python 3.9+

  • pip

Install dependencies:

pip install -r requirements.txt

Run the server locally over HTTP:

python my_server.py

The MCP endpoint will be available at http://localhost:8000/mcp.

Optional: Test with a simple client script.

Create client_test.py:

import asyncio
from fastmcp import Client

async def main():
    async with Client("http://localhost:8000/mcp") as client:
        result = await client.call_tool("greet", {"name": "FastMCP"})
        print(result)

asyncio.run(main())

Run it:

python client_test.py

Deploy to FastMCP Cloud

FastMCP Cloud hosts MCP servers from your GitHub repository and provides a URL like https://your-project-name.fastmcp.app/mcp ([1]).

Steps:

  • Push this repository to GitHub (ensure requirements.txt is present).

  • Sign in to FastMCP Cloud with your GitHub account and create a project.

  • Set the entrypoint to my_server.py:mcp (Cloud imports the server object and ignores __main__) ([2]).

  • Deploy; your server becomes available at https://<project>.fastmcp.app/mcp.

Notes:

  • Cloud automatically installs dependencies from requirements.txt ([1]).

  • Entry-point configuration accepts file.py:object_name syntax if you rename the server instance ([1]).

References

  • [1] FastMCP Cloud guide: https://gofastmcp.com/deployment/fastmcp-cloud

  • [2] FastMCP Quickstart: https://gofastmcp.com/getting-started/quickstart

-
security - not tested
F
license - not found
-
quality - not tested

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zongjieshen/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server