← Back to directory

Garmin MCP Server

Community

MCP server for accessing Garmin data, with 110+ tools covering fitness, health, and training analytics.

GitHub source repository ↗

★ 1.1k Stars Category · Other Very popular Source revision 3610be6feed9

72FMRS · B

Reliability

11/20

Security and permissions

14/20

Maintenance

16/20

Documentation

17/20

Setup experience

14/20

The Garmin MCP server offers extensive coverage of Garmin Connect data, ideal for users wanting to integrate fitness and health data into AI workflows. Installation is straightforward, supports multiple clients, but requires attention to authentication and HTTP security.

Read the FMRS scoring method →

The Garmin MCP server connects to Garmin Connect and exposes your fitness and health data to Claude and other MCP-compatible clients. It leverages the python-garminconnect library and offers 110+ tools covering activity management, health metrics, training load trends, power analysis, and more, including advanced features like power duration curve, FIT file parsing, and DI2 electronic shift intelligence. It supports tool filtering via environment variables and provides high-level workout builder tools.

Tools

The tool list has not been reviewed yet.

Setup

Authenticate once using garmin-mcp-auth to save OAuth tokens to ~/.garminconnect.
Add the server configuration in Claude Desktop or any MCP client using the uvx command.
Restart your client to access your Garmin data.

claude_desktop_config.json

{
  "mcpServers": {
    "garmin": {
      "command": "uvx",
      "args": [
        "--python",
        "3.12",
        "--from",
        "git+https://github.com/Taxuspt/garmin_mcp",
        "garmin-mcp"
      ]
    }
  }
}

Generate and validate client config

Fit and risk

Best for

Garmin users wanting to centralize fitness data in AI assistants
Runners or cyclists needing automated workout generation and scheduling
Analytical users who prefer natural language queries for health trends
Developers and hobbyists integrating Garmin data into custom toolchains

Not for

Non-Garmin users or those without a Garmin account
Applications requiring real-time GPS tracking or instant data push
Users who want to bypass authentication (requires Garmin account and OAuth tokens)
Destructive operations like deleting activities (not implemented for safety)

Required permissions

Read and edit Garmin Connect data (activities, health metrics, workouts, etc.)
Download activity files to local directory
Create and schedule workout plans
Access user's health metrics and body composition data

Risks and side effects

Stores OAuth tokens which expire after ~6 months, requiring re-authentication
HTTP transport has no authentication; if exposed on public network, place behind a reverse proxy
Some destructive operations (e.g., delete activity) are intentionally not implemented to avoid accidents
Many tools may increase LLM context overhead, but can be filtered via environment variables

Troubleshooting

Ensure `uvx` is in PATH, or use the full path
Check Garmin credentials correctness and MFA status
Check logs: macOS: `~/Library/Logs/Claude/mcp-server-garmin.log`, Windows: `%APPDATA%\Claude\logs\mcp-server-garmin.log`
If tokens expired, run `garmin-mcp-auth --force-reauth`
Verify network connectivity and Garmin service availability

Use cases

View recent activities and detailed activity information

Analyze health metrics like sleep, stress, heart rate

Track training status, CTL/ATL/TSB, HRV, VO2 max trends

Create and schedule running, walking, strength workouts

Download activity files in FIT, GPX, TCX, or CSV format

Analyze cycling power, FIT files, and DI2 shifting data

Supported clients

Claude DesktopFull support

CodexFull support

opencodeFull support

Related MCP servers

Compare with other MCP servers