MCP Examples

🚀 MCP Examples Project

This project showcases the setup of a Model Context Protocol (MCP) server and client. It includes tools and configurations for running the server within a Docker container.

🚀 Quick Start

✨ Features

• Demonstrates a Model Context Protocol (MCP) server and client setup.
• Provides tools and configuration for running the server in a Docker container.

📦 Installation

Setting Up and Building the Docker Image

1. Build the Docker Image From the project root, run the following command:

   docker build -t mcp-example-stdio-server:latest .
   

   This command will create a Docker image named mcp-example-stdio-server:latest that contains the MCP server.
2. Run the Server (Standalone) You can run the server directly using the command below:

   docker run --rm -i mcp-example-stdio-server:latest
   

   The server will start and listen for MCP stdio requests.

💻 Usage Examples

mcp.json Configuration

The .vscode/mcp.json file configures how the MCP server is launched in development environments (such as VS Code):

{
  "servers": {
    "example-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "mcp-example-stdio-server:latest"
      ]
    }
  },
  "inputs": []
}

• type: stdio indicates that the server communicates over standard input/output.
• command: The command to launch the server (docker).
• args: Arguments to run the Docker container with the built image. This setup allows development tools to start the MCP server in a containerized environment automatically.

📚 Documentation

Project Structure

.
├── Dockerfile                # Docker build instructions for the MCP server
├── pyproject.toml            # Python project configuration
├── uv.lock                   # Lock file for dependencies
├── README.md                 # Project documentation
├── client/                   # Client-side code (if any)
└── servers/                  # MCP server implementation
    ├── __init__.py
    ├── main.py               # Main entry point for the server
    └── tools/                # Additional server tools
        ├── __init__.py
        ├── calendar.py       # Calendar tool implementation
        ├── task_manager.py   # Task manager tool implementation
        └── weather.py        # Weather tool implementation

🔧 Technical Details

• Ensure Docker is installed and running on your system.
• Update the Docker image as needed after making changes to the server code by rebuilding the image.
• The servers/tools/ directory contains modular tool implementations that can be extended as needed.