Garmin MCP Server
This Model Context Protocol (MCP) server connects to Garmin Connect and exposes your fitness and health data to Claude and other MCP-compatible clients.
README
Garmin MCP Server
This Model Context Protocol (MCP) server connects to Garmin Connect and exposes your fitness and health data to Claude and other MCP-compatible clients.
Features
- List recent activities
- Get detailed activity information
- Access health metrics (steps, heart rate, sleep)
- View body composition data
Setup
Local Development
- Install the required packages on a new environment:
uv sync
Remote Deployment (Railway)
Want to host this MCP server remotely and access it from AI assistants like Poke? See:
- SETUP_GUIDE.md - Quick start guide
- RAILWAY_DEPLOYMENT.md - Detailed deployment instructions
- Quick deploy: Run
./deploy_to_railway.sh(requires Railway CLI)
Running the Server
Configuration
Your Garmin Connect credentials are read from environment variables:
GARMIN_EMAIL: Your Garmin Connect email addressGARMIN_EMAIL_FILE: Path to a file containing your Garmin Connect email addressGARMIN_PASSWORD: Your Garmin Connect passwordGARMIN_PASSWORD_FILE: Path to a file containing your Garmin Connect password
File-based secrets are useful in certain environments, such as inside a Docker container. Note that you cannot set both GARMIN_EMAIL and GARMIN_EMAIL_FILE, similarly you cannot set both GARMIN_PASSWORD and GARMIN_PASSWORD_FILE.
With Claude Desktop
- Create a configuration in Claude Desktop:
Edit your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add this server configuration:
{
"mcpServers": {
"garmin": {
"command": "uvx",
"args": [
"--python",
"3.12",
"--from",
"git+https://github.com/Taxuspt/garmin_mcp",
"garmin-mcp"
],
"env": {
"GARMIN_EMAIL": "YOUR_GARMIN_EMAIL",
"GARMIN_PASSWORD": "YOUR_GARMIN_PASSWORD"
}
}
}
}
Replace the path with the absolute path to your server file.
- Restart Claude Desktop
With MCP Inspector
For testing, you can use the MCP Inspector from the project root:
npx @modelcontextprotocol/inspector uv run garmin-mcp
Usage Examples
Once connected in Claude, you can ask questions like:
- "Show me my recent activities"
- "What was my sleep like last night?"
- "How many steps did I take yesterday?"
- "Show me the details of my latest run"
Security Note
Troubleshooting
If you encounter login issues:
- Verify your credentials are correct
- Check if Garmin Connect requires additional verification
- Ensure the garminconnect package is up to date
For other issues, check the Claude Desktop logs at:
- macOS:
~/Library/Logs/Claude/mcp-server-garmin.log - Windows:
%APPDATA%\Claude\logs\mcp-server-garmin.log
Garming Connect one-time code
If you have one-time codes enabled in your account, you need to login at the command line first to set the token in the interactive cli.
The app expects either the env var GARMIN_EMAIL or GARMIN_EMAIL_FILE. You can store these in files with the following command.
echo "your_email@example.com" > ~/.garmin_email
echo "your_password" > ~/.garmin_password
chmod 600 ~/.garmin_email ~/.garmin_password
Then you can manually run the login script.
GARMIN_EMAIL_FILE=~/.garmin_email GARMIN_PASSWORD_FILE=~/.garmin_password uvx --python 3.12 --from git+https://github.com/Taxuspt/garmin_mcp garmin-mcp
You will likely see
Garmin Connect MFA required. Please check your email/phone for the code.
Enter MFA code: XXXXXX
Oauth tokens stored in '~/.garminconnect' directory for future use. (first method)
Oauth tokens encoded as base64 string and saved to '~/.garminconnect_base64' file for future use. (second method)
After setting the token at the cli, you can use the following in Claude, without the env vars because the Oauth tokens have been set.
"garmin": {
"command": "uvx",
"args": [
"--python",
"3.12",
"--from",
"git+https://github.com/Taxuspt/garmin_mcp",
"garmin-mcp"
]
}
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。
