Simple MCP Server (FastMCP)

This repository demonstrates how to create, test, and deploy a simple remote MCP server using FastMCP, uv, and GitHub.

Prerequisites

Make sure you have the following installed:

• Python 3.10+

• uv (Python package manager)

• Git

• VS Code (recommended)

• Node.js (for MCP Inspector)

Related MCP server: MCP Template

Step-by-Step Guide

1. Install uv

uv is a fast Python package manager and runtime.

pip install uv

2. Create a new project folder

mkdir simple-mcp-server
cd simple-mcp-server

3. Open the folder in VS Code

code .

4. Initialize the project

uv init

This creates:

• pyproject.toml

• Virtual environment configuration

5. Install FastMCP

uv add fastmcp

FastMCP allows you to build MCP-compatible servers easily.

6. Create a simple server

Create a file called main.py:

from fastmcp import FastMCP

mcp = FastMCP("Simple MCP Server")

@mcp.tool()
def hello(name: str) -> str:
    return f"Hello, {name}! Welcome to MCP."

if __name__ == "__main__":
    mcp.run()

7. Run the server

uv run main.py

Your MCP server will start locally.

8. Test using MCP Inspector

Use MCP Inspector to:

• Connect to the server

• Verify tools are listed

• Send test requests

This confirms your server is MCP-compliant.

9. Create a GitHub repository

Create a new repo on GitHub named:

simple-mcp-server

10. Initialize Git locally

git init
git add .
git commit -m "Initial commit: Simple MCP server"

11. Add GitHub remote & push

git remote add origin https://github.com/yourusername/simple-mcp-server.git
git push -u origin main

12. Deploy on FastMCP Cloud

1. Create an account on FastMCP Cloud

2. Connect your GitHub repository

3. Deploy the project

After deployment:

• Your MCP server gets a public endpoint

• It can be used by MCP clients and LLM agents

Project Structure

simple-mcp-server/
│── main.py
│── pyproject.toml
│── README.md

Next Steps

• Add more MCP tools

• Connect this server to LLM agents

• Add authentication & logging

Happy building 🚀