Garmin
Enables ChatGPT to access and analyze personal Garmin health data including daily steps, heart rate, calories, sleep duration, and body battery levels. Collects data via webhook from Garmin devices and provides health insights through natural languag
What is Garmin?
Garmin is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables chatgpt to access and analyze personal garmin health data including daily steps, heart rate, calories, sleep duration, and body battery levels. collects data via webhook from garmin devices an...
Enables ChatGPT to access and analyze personal Garmin health data including daily steps, heart rate, calories, sleep duration, and body battery levels. Collects data via webhook from Garmin devices and provides health insights through natural languag
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables ChatGPT to access and analyze personal Garmin health
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx garmin-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Garmin
The Garmin MCP Server connects AI assistants to your personal Garmin Connect data, exposing 110+ tools spanning activity management, health and wellness metrics (steps, sleep, heart rate, body battery, HRV), training performance analytics (VO2 max, CTL/ATL/TSB training load), workout management, nutrition tracking, gear management, and device information. It authenticates via your Garmin Connect credentials and supports a one-click .dxt installation for Claude Desktop as well as Docker-based deployments for production use.
Prerequisites
- Python 3.12+ installed (for uv/uvx installation method)
- A Garmin Connect account with data synced from your Garmin device
- uv package manager installed (pip install uv or brew install uv)
- An MCP-compatible client such as Claude Desktop
Pre-authenticate with Garmin Connect
Run the one-time authentication command to log in to Garmin Connect and save OAuth tokens locally. You will be prompted for your email and password; if you have MFA enabled, you will need to complete that step too.
uvx --python 3.12 --from git+https://github.com/Taxuspt/garmin_mcp garmin-mcp-authVerify authentication tokens are saved
Run the verification command to confirm the saved tokens are valid and the server can reach Garmin Connect successfully.
garmin-mcp-auth --verifyAdd the server to Claude Desktop
Edit your Claude Desktop configuration to register the Garmin MCP server. After the pre-auth step, you do not need to embed credentials in the config — the saved tokens are used automatically. Optionally set GARMIN_EMAIL and GARMIN_PASSWORD as fallback.
Restart Claude Desktop
Quit and reopen Claude Desktop. The Garmin MCP server will start and the 110+ health and fitness tools will be available in your conversations.
Query your health data
Start a conversation in Claude Desktop and ask about your Garmin data. The server handles the Garmin Connect API calls automatically and returns your personal metrics.
Garmin Examples
Client configuration
Add this to your claude_desktop_config.json. After running garmin-mcp-auth, tokens are stored locally so GARMIN_EMAIL and GARMIN_PASSWORD are optional fallbacks. For China users, set GARMIN_IS_CN to true.
{
"mcpServers": {
"garmin": {
"command": "uvx",
"args": ["--python", "3.12", "--from", "git+https://github.com/Taxuspt/garmin_mcp", "garmin-mcp"],
"env": {
"GARMIN_EMAIL": "[email protected]",
"GARMIN_PASSWORD": "your-garmin-password",
"GARMIN_FIT_DOWNLOAD_DIR": "/Users/yourname/garmin-activities"
}
}
}
}Prompts to try
After configuring the Garmin MCP server in Claude Desktop, use these prompts to analyze your fitness and health data.
- "Show me my recent activities from the past week."
- "What was my sleep duration and quality score last night?"
- "Analyze my training load — show my CTL, ATL, and TSB trend for the past 6 weeks."
- "What is my current VO2 max and how has it changed over the past month?"
- "Summarize my daily steps, calories burned, and body battery levels for this week."Troubleshooting Garmin
Authentication fails with 'invalid credentials' or MFA prompt errors
Run 'uvx --python 3.12 --from git+https://github.com/Taxuspt/garmin_mcp garmin-mcp-auth' interactively in your terminal to complete the login flow including any MFA steps. The saved tokens will then be used by the MCP server automatically.
Server starts but returns empty or no data for health queries
Confirm your Garmin device has synced data to Garmin Connect recently. Open garmin.com/modern/proxy/wellness-service/wellness/dailySummaryChart and verify data is visible in the web interface. Also check that GARMIN_ENABLED_TOOLS is not set to an empty string which would disable all tools.
uvx command fails or Python 3.12 is not available
Install uv with 'pip install uv' or 'brew install uv'. If Python 3.12 is not installed, uv will download it automatically when you use the '--python 3.12' flag. Alternatively, install Python 3.12 directly from python.org and retry.
Frequently Asked Questions about Garmin
What is Garmin?
Garmin is a Model Context Protocol (MCP) server that enables chatgpt to access and analyze personal garmin health data including daily steps, heart rate, calories, sleep duration, and body battery levels. collects data via webhook from garmin devices and provides health insights through natural languag It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Garmin?
Follow the installation instructions on the Garmin GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Garmin?
Garmin works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Garmin free to use?
Yes, Garmin is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Garmin Alternatives — Similar Analytics Servers
Looking for alternatives to Garmin? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
Browse More Analytics MCP Servers
Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Garmin in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Garmin?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.