Garmin Connect MCP server

The Garmin Connect MCP Server provides a convenient interface for interacting with the Garmin Connect API, allowing you to manage your workouts, health metrics, and other Garmin data through a server that implements the Model Context Protocol.

Prerequisites

Before setting up the server, ensure you have:

• Python 3.x installed on your system
• A Garmin Connect account
• Access to your Garmin login credentials

Installation

Step 1: Install Required Packages

Install the required Python packages using the uv package manager:

uv sync

Alternatively, you can install the dependencies manually, which includes the Python Garmin Connect package that enables interaction with Garmin Connect API.

Step 2: Set Up Environment Variables

Create a .env file in the root directory of the project based on the provided template:

1. Copy the .env_template file to create a new .env file
2. Add your Garmin credentials to the file:

   [email protected]
   GARMIN_PASSWORD=your_password
   

Authentication

You'll need to generate an authentication token to connect to Garmin:

python example.py

This command will authenticate with Garmin Connect using your credentials and generate the necessary token for API interaction.

Using the MCP Server

Development Mode

To run the server in development mode with the MCP Inspector interface:

mcp dev garmin_mcp_server.py

This provides a development environment where you can test and inspect the server's functionality.

Installing in Claude Desktop

To make the Garmin MCP server available in Claude Desktop:

mcp install garmin_mcp_server.py

After installation, Claude will be able to access your Garmin data through the MCP server, allowing you to query and manage your Garmin information directly through the Claude interface.

Usage Examples

Once the server is running, you can interact with your Garmin data through Claude by:

• Asking about recent workouts
• Retrieving health metrics
• Managing Garmin device information
• Analyzing activity data

The MCP server handles the communication between Claude and the Garmin Connect API, ensuring secure and efficient data transfer.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.