Garmin MCP Server
Integrates with Garmin Connect to retrieve activity data, health metrics, and provide AI-powered training insights and personalized coaching recommendations based on your fitness activities and performance trends.
README
Garmin MCP Server
A Model Context Protocol (MCP) server that integrates with Garmin Connect to provide activity insights and training suggestions for Claude Desktop.
Features
- Activity Tracking: Retrieve recent activities from Garmin Connect
- Activity Insights: Get detailed analysis of individual activities or activity patterns
- Training Suggestions: AI-powered recommendations based on your training data and health metrics
- Health Metrics: Access to comprehensive health data including heart rate, sleep, stress, and body battery
- Performance Analysis: Automated analysis of training load, recovery, and performance trends
Installation
-
Clone or download this repository
-
Install dependencies:
cd garmin-mcp npm install -
Build the TypeScript code:
npm run build
Configuration
Environment Variables Setup (Recommended)
For security and convenience, you can store your Garmin Connect credentials in environment variables:
-
Create a .env file:
touch .env -
Add your credentials to the .env file:
# .env GARMIN_USERNAME=your.email@example.com GARMIN_PASSWORD=your_secure_password GARMIN_AUTO_AUTH=true -
Secure the file:
chmod 600 .env
With environment variables configured, the MCP server will:
- Automatically authenticate on startup (if
GARMIN_AUTO_AUTH=true) - Use your stored credentials as fallback for authentication commands
- Keep your credentials secure and out of version control
Claude Desktop Setup
Add the MCP server to your Claude Desktop configuration:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\\Claude\\claude_desktop_config.json
{
"mcpServers": {
"garmin": {
"command": "node",
"args": ["path/to/garmin-mcp/dist/index.js"]
}
}
}
Triathlon Expert Mode (Recommended)
For the best coaching experience, add the triathlon expert prompt to your Claude project:
- Create or open your project in Claude Desktop
- Add the expert prompt by copying the contents of
TRIATHLON_EXPERT_PROMPT.mdto your project's context - Enable code execution in your project settings for accurate calculations
This prompt transforms Claude into a world-class triathlon coach that:
- Uses code for all calculations to prevent estimation errors
- Provides data-driven training insights
- Offers personalized coaching based on your Garmin data
- Analyzes performance trends with scientific accuracy
Garmin Connect Authentication
The MCP server supports multiple authentication methods:
Option 1: Environment Variables (Recommended)
Set up your .env file as described above. The server will automatically authenticate on startup.
Option 2: Manual Authentication
Use the authenticate_garmin tool within Claude Desktop. If you have environment variables set, you can simply call:
- "Please authenticate with Garmin Connect" (uses env vars)
- Or provide credentials manually: "Authenticate with username X and password Y"
Important: Credentials are only stored in memory during the session and are not persisted to disk.
Available Tools
1. authenticate_garmin
Authenticate with Garmin Connect using your username and password.
Parameters:
username: Your Garmin Connect usernamepassword: Your Garmin Connect password
2. get_activities
Retrieve recent activities from Garmin Connect.
Parameters:
days(optional): Number of days to look back (default: 30)limit(optional): Maximum number of activities to return (default: 50)
3. get_activity_insights
Get detailed insights for a specific activity or recent activities.
Parameters:
activityId(optional): Specific activity ID to analyzedays(optional): Number of days to analyze if no activity ID specified (default: 7)
4. get_training_suggestions
Get AI-powered training suggestions based on recent activities and performance.
Parameters:
activityType(optional): Type of activity to focus on ('running', 'cycling', 'swimming', 'strength', 'all')days(optional): Number of days of history to consider (default: 14)
5. get_health_metrics
Get health and wellness metrics from Garmin Connect.
Parameters:
startDate(optional): Start date in YYYY-MM-DD formatendDate(optional): End date in YYYY-MM-DD formatmetrics(optional): Specific metrics to retrieve (['heartRate', 'stress', 'sleep', 'bodyBattery', 'vo2Max'])
Usage Examples
Getting Started
- Authenticate: "Please authenticate with my Garmin Connect account"
- View Recent Activities: "Show me my recent activities"
- Get Insights: "Analyze my running performance from the last week"
- Training Advice: "Give me training suggestions based on my recent workouts"
Detailed Analysis
- "What are my sleep patterns and how do they affect my recovery?"
- "Analyze my heart rate trends during cycling activities"
- "Give me specific recommendations for improving my running pace"
- "How is my training load compared to my recovery metrics?"
Data Privacy
- This MCP server accesses your Garmin Connect data only during active sessions
- No data is stored permanently on your device
- Authentication credentials are not persisted between sessions
- All data processing happens locally on your machine
Dependencies
@modelcontextprotocol/sdk: MCP SDK for TypeScriptgarmin-connect: Unofficial Garmin Connect API clientzod: Schema validation
Development
To run in development mode:
npm run dev
To build:
npm run build
Limitations
- Requires valid Garmin Connect credentials
- Depends on the unofficial Garmin Connect API (may break with Garmin updates)
- Some advanced metrics may not be available depending on your Garmin device
- Rate limiting by Garmin Connect may apply
Troubleshooting
Authentication Issues
- Ensure your Garmin Connect credentials are correct
- Check if your account requires two-factor authentication (not currently supported)
- Verify your account is not locked or suspended
Missing Data
- Some metrics require specific Garmin devices
- Ensure your device is synced with Garmin Connect
- Check that the requested date range contains activities
Connection Issues
- Verify your internet connection
- Check if Garmin Connect services are operational
- Try authenticating again if the session has expired
License
MIT License - see LICENSE file for details
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。