by matin
Integrate Garth with Garmin Connect to access fitness data from your Garmin watch for fitness tracking, including sleep
Connects to Garmin Connect to retrieve your fitness and health data including sleep patterns, stress levels, activities, and body metrics. Requires Garmin account authentication.
Garth (Garmin Connect) is a community-built MCP server published by matin that provides AI assistants with tools and capabilities via the Model Context Protocol. Integrate Garth with Garmin Connect to access fitness data from your Garmin watch for fitness tracking, including sleep It is categorized under developer tools, analytics data.
You can install Garth (Garmin Connect) in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Garth (Garmin Connect) is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Garth (Garmin Connect) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
According to our notes, Garth (Garmin Connect) benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Useful MCP listing: Garth (Garmin Connect) is the kind of server we cite when onboarding engineers to host + tool permissions.
Garth (Garmin Connect) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
I recommend Garth (Garmin Connect) for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Garth (Garmin Connect) reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Garth (Garmin Connect) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
We evaluated Garth (Garmin Connect) against two servers with overlapping tools; this profile had the clearer scope statement.
We wired Garth (Garmin Connect) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Garth (Garmin Connect) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
showing 1-10 of 35
Garmin Connect MCP server based on garth.
{
"mcpServers": {
"Garth - Garmin Connect": {
"command": "uvx",
"args": [
"garth-mcp-server"
],
"env": {
"GARTH_TOKEN": "<output of `uvx garth login`>"
}
}
}
}
Make sure the path for the uvx command is fully scoped as MCP doesn't
use the same PATH your shell does. On macOS, it's typically
/Users/{user}/.local/bin/uvx.
By default, all 30 tools are exposed. To reduce context size for LLM usage, you can filter tools using environment variables.
{
"mcpServers": {
"Garth - Garmin Connect": {
"command": "uvx",
"args": ["garth-mcp-server"],
"env": {
"GARTH_TOKEN": "<token>",
"GARTH_ENABLED_TOOLS": "get_activities,get_activity_details,daily_steps,nightly_sleep"
}
}
}
}
"env": {
"GARTH_TOKEN": "<token>",
"GARTH_DISABLED_TOOLS": "get_gear,get_gear_stats,get_device_settings,get_connectapi_endpoint"
}
Tool names are case-insensitive and comma-separated. If GARTH_ENABLED_TOOLS
is set, GARTH_DISABLED_TOOLS is ignored.
user_profile - Get user profile informationuser_settings - Get user settings and preferencesnightly_sleep - Get detailed sleep data with optional movement datadaily_sleep - Get daily sleep summary datadaily_stress / weekly_stress - Get stress datadaily_intensity_minutes / weekly_intensity_minutes - Get intensity minutesdaily_body_battery - Get body battery datadaily_hydration - Get hydration datadaily_steps / weekly_steps - Get steps datadaily_hrv / hrv_data - Get heart rate variability dataget_activities - Get list of activities with optional filtersget_activities_by_date - Get activities for a specific dateget_activity_details - Get detailed activity informationget_activity_splits - Get activity lap/split dataget_activity_weather - Get weather data for activitiesget_body_composition - Get body composition dataget_respiration_data - Get respiration dataget_spo2_data - Get SpO2 (blood oxygen) dataget_blood_pressure - Get blood pressure readingsget_devices - Get connected devicesget_device_settings - Get device settingsget_gear - Get gear informationget_gear_stats - Get gear usage statisticsmonthly_activity_summary - Get monthly activity overviewsnapshot - Get snapshot data for date rangesget_connectapi_endpoint - Direct access to any Garmin Connect API endpointPrerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.