MCP Server Templates

🚀 MCP Server Templates

This repository offers a template for setting up an MCP (Model Context Protocol) server for local development. It includes examples of different MCP server implementations:

1. Weather API - Provides weather alerts and forecasts.
2. Calculator - Performs basic and advanced mathematical operations.
3. Notes - Offers a simple note-taking function with local file storage.

⚠️ Important Note

This project requires Python 3.10 or higher. For instructions on using the correct Python version, see the footnotes.

✨ Features

• Multiple MCP server implementations for different use - cases.
• Integration with VS Code as language servers.
• Support for parallel dependency installation using the UV package manager.

📦 Installation

Requirements

• Python 3.10+
• FastMCP library
• Other dependencies listed in requirements.txt
• UV package manager (recommended for faster installation)

Setup Steps

1. Clone the repository:

   git clone <repository-url>
   cd mcp-server-templates
   

2. Create a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   

3. Install the UV package manager (if not already installed):

   pip install uv
   

4. Install dependencies using UV:

   uv pip install -r requirements.txt
   

💻 Usage Examples

Running MCP Servers

Each MCP server can be run using the MCP development server command:

Weather API Server

mcp dev servers/weather.py

The Weather API provides the following tools:

• get_alerts: Retrieve weather alerts for US states.
• get_forecast: Get the weather forecast for a location based on latitude and longitude.

Calculator Server

mcp dev servers/calculator.py

The calculator offers mathematical operations, including:

• Basic operations: addition, subtraction, multiplication, and division.
• Advanced operations: square root, exponentiation, etc.
• Support for parentheses and consecutive operations.

Notes Server

mcp dev servers/notes.py

The Notes server provides the following functions:

• create_note: Create a new note.
• retrieve_note: Retrieve a note by ID.
• update_note: Update an existing note.
• delete_note: Delete a note.
• list_notes: List all notes.

VS Code Integration

When using in VS Code, you can install the servers as language servers and provide the following configuration:

{
    "mcp.servers": {
        "calculator": {
            "path": "servers/calculator.py",
            "args": []
        },
        "notes": {
            "path": "servers/notes.py",
            "args": []
        },
        "weather": {
            "path": "servers/weather.py",
            "args": []
        }
    }
}

📚 Documentation

Project Structure

├── servers/          # MCP server implementations
│   ├── calculator.py # Calculator server implementation
│   ├── notes.py      # Notes server implementation
│   └── weather.py    # Weather API server implementation
├── docs/             # Documentation
├── requirements.txt  # Python dependencies
└── README.md         # This file

Footnotes

1. Python Version Requirement:

   • It is recommended to use Python 3.8 or higher.
   • Methods for installing the specified Python version include using pyenv, virtualenv, or Anaconda.

2. Example of Using Pyenv:

   # Install pyenv and set the Python version
   brew install pyenv
   pyenv install 3.10
   pyenv global 3.10
   
   # Activate the virtual environment (optional)
   python -m venv mcp_env
   source mcp_env/bin/activate
   

3. Example of Using in Anaconda:

   conda create -n mcp python=3.10
   conda activate mcp
   pip install uv
   uv pip install -r requirements.txt
   

4. Dependency Management Tips:

   • Using uv allows for parallel installation of dependencies, accelerating the installation process.
   • For dependencies of a specific Python version, refer to requirements.txt.

5. Runtime Precautions:

   • Ensure that all dependencies are correctly installed.
   • Conduct thorough testing and optimization before using in a production environment.

📄 License

• Introduction to MCP and Official Documentation
• MCP Python Package on PyPI