Garmin MCP Lite

🚀 Garmin MCP Lite

Read this in other languages: English, 简体中文.

A lightweight Garmin Model Context Protocol (MCP) server designed specifically for endurance athletes.

It exposes 12 precisely-curated endpoints for deep analysis of running, cycling, swimming, and health data — replacing bulky 80+ endpoint alternatives with a clean, focused toolset.

🤖 [For AI Assistants & LLMs]

You are interfacing with a Garmin MCP (Model Context Protocol) server.

1. Data Freshness: Always query the data if the user asks about their recent workouts or health metrics.
2. Parameter Tuning: Use the fields parameter in tools like garmin_activity_detail to limit the response payload and save context window (e.g., ["splits", "hrZones"]).
3. Read-Only: This server provides read-only access to Garmin Connect. You cannot modify user data.
4. No Password Request: Never ask the user for their Garmin password. Authentication is handled out-of-band via a local token.
5. Health Tip: garmin_health now supports a metric parameter — use "steps", "sleep", "hrv", "spo2", "body_battery", etc., to query specific data and save context window.

📚 Table of Contents

• ✨ Core Tools
• 🚀 Quickstart
• 🛠️ Manual Installation
• 💬 Example Queries
• ⚖️ Comparison with Other Garmin MCPs
• 📄 License

✨ Core Tools

12 exactly-scoped tools, grouped by domain:

🏃 Activity & Training

💚 Health & Wellness

🎯 Goals & Challenges

⌚ Device & Gear

🚀 Quickstart (via PyPI & uv)

The easiest way to run this server is using uvx — no cloning required.

1️⃣ Authenticate (First Time Only)

💡 Why not just put the password in the AI config?

Garmin has strict security measures. Logging in from a new location/MCP server often triggers Cloudflare CAPTCHAs or MFA email codes. If the password is in Claude's background config, the AI assistant will silently freeze or fail when challenged, with no way for you to input the code.

Therefore, this plugin uses a secure two-step strategy: Run a login script in your terminal first. If challenged, you can interactively input the MFA code. Upon success, a session token is cached locally (valid for ~1 year).

GARMIN_EMAIL="your@email.com" GARMIN_PASSWORD="your_password" uvx --with garmin-mcp-lite garmin-mcp-lite-login

🇨🇳 China Region Users: If your account is registered in Garmin China (garmin.cn), prefix the command with GARMIN_IS_CN=true.

2️⃣ Configure Your AI Assistant

Once authenticated, add the server to your favorite MCP-compatible AI assistant.

🖥️ Claude Desktop

Add this to your ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "garmin-lite": {
      "command": "uvx",
      "args": [
        "garmin-mcp-lite"
      ]
    }
  }
}

🔌 Cursor / Windsurf / Gemini CLI / Other MCP Clients

Use the exact same command and args as above. The server will automatically load the cached token from ~/.garmin-mcp-lite/garmin_tokens.json.

🛠️ Manual Installation (for Developers)

If you want to modify the code:

git clone https://github.com/Golden0Voyager/garmin-mcp-lite.git
cd garmin-mcp-lite
uv sync

# Login
GARMIN_EMAIL="your@email.com" GARMIN_PASSWORD="your_password" python -m garmin_mcp_lite.login

# Run server
python -m garmin_mcp_lite.server

💬 Example Queries

Once connected, you can ask your AI assistant natural-language questions like:

• "What's my training load focus this week?"
• "Show me my race goal for June and what my current predicted finish time is."
• "How's my Grossglockner virtual climb challenge going?"
• "Is my Descent G1 firmware up to date?"
• "How many steps have I taken today? Am I on track for my daily goal?"
• "Analyze my sleep quality from last night."

⚖️ Comparison with Other Garmin MCPs

📄 License

MIT © 2026 Haining Yu

This project is built on top of the excellent garminconnect library. It is not an official Garmin product. Please adhere to Garmin Connect's terms of service when using this tool.