MCP Server Example

🚀 MCP Server Example Implementation

This repository contains an educational implementation of a Model Context Protocol (MCP) server. The code demonstrates how to build a functional MCP server that can integrate with various LLM clients.

To view the full tutorial, please refer to the YouTube video tutorial.

🚀 Quick Start

Install the uv Package Manager

On MacOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Make sure to restart your terminal afterward so that the uv command takes effect.

Project Setup

1. Create and initialize the project:

# Create a new directory for our project
uv init mcp-server
cd mcp-server

# Create a virtual environment and activate it
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

2. Install dependencies:

uv add "mcp[cli]" httpx

3. Create the server implementation file:

touch main.py

Run the Server

1. Start the MCP server:

uv run main.py

2. The server starts and is ready to accept connections.

✨ Features

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context for LLMs. Imagine MCP as a USB-C port, providing a standard way for AI applications to connect to different data sources and tools.

Key Advantages

• A growing list of pre-built integrations that your LLM can plug into directly.
• Flexibility to easily switch between different LLM providers and vendors.
• Best practices for data protection within your infrastructure.

Architecture Overview

MCP uses a client-server architecture, where host applications can connect to multiple servers:

• MCP Host: Applications such as Claude Desktop, IDEs, or AI tools that want to access MCP data.
• MCP Client: A protocol client that maintains a one-to-one connection with the server.
• MCP Server: A lightweight program that exposes specific functionality through a standardized model context protocol.
• Data Sources: Local (files, databases) and remote services (APIs) that the MCP server can access.

MCP Core Concepts

MCP servers can provide three main types of capabilities:

• Resources: File-like data that clients can read (e.g., API responses or file contents).
• Tools: Functions that LLMs can call (with user approval).
• Prompts: Pre-written templates to help users complete specific tasks.

📦 Installation

System Requirements

• Python 3.10 or higher
• MCP SDK 1.2.0 or higher
• uv package manager

📚 Documentation

Connecting to Claude Desktop

1. Install Claude Desktop from the official website.
2. Configure Claude Desktop to use your MCP server: Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
    "mcpServers": {
        "mcp-server": {
            "command": "uv",  # It is recommended to use the absolute path of the uv command
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/YOUR/mcp-server",
                "run",
                "main.py"
            ]
        }
    }
}

3. Restart Claude Desktop.

Troubleshooting

If your server is not detected by Claude Desktop:

1. Check the configuration file path and permissions.
2. Ensure that the absolute path in the configuration is correct.
3. Ensure that uv is installed correctly and accessible.
4. Check the Claude Desktop logs for error information.

📄 License

This project is released under the MIT License. For more details, please refer to the LICENSE file.