Which integrations are available for this server?

Provides tools to access health and fitness data from Garmin Connect, including workouts, sleep, heart rate, body composition, fitness metrics, and activity file downloads.

How do I use garmin-mcp-server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@garmin-mcp-server What's my training readiness today?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

garmin-mcp-server

by JohanBellander

Overview Schema Source Related Servers Discussions Admin

Python

Local

Garmin Connect MCP Server

A Model Context Protocol (MCP) server that connects AI assistants to your Garmin Connect health and fitness data. Ask Claude, ChatGPT, OpenCode, or any MCP-compatible client about your workouts, sleep, heart rate, and more -- using natural language.

Built on python-garminconnect and the MCP Python SDK.

Features

29 tools across 6 categories, giving your AI assistant access to:

Category	Tools	Examples
Health	5	Daily summary, heart rate, sleep stages, stress, body battery
Activities	4	Recent workouts, search by date/type, detailed splits
Body	3	Weight trends, body composition, hydration tracking
Fitness	6	Training readiness, VO2 Max, HRV, race predictions, endurance score
Devices	6	Device info, step trends, personal records, SpO2, respiration, goals
Export	5	Download FIT, GPX, TCX, KML, and CSV files

Related MCP server: garth-mcp-server

Quick Start

Prerequisites

Python 3.10+
uv package manager
A Garmin Connect account with a paired device

1. Clone and install

git clone https://github.com/JohanBellander/garmin-mcp-server.git
cd garmin-mcp-server
uv sync

2. Authenticate with Garmin

Run the one-time setup to save your OAuth tokens:

uv run garmin-mcp-setup

You'll be prompted for your email, password, and MFA code (if enabled). Tokens are saved to ~/.garminconnect/ and last approximately one year -- you won't need to re-authenticate until they expire.

3. Connect to your AI assistant

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "garmin": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/garmin-mcp-server",
        "run",
        "garmin-mcp-server"
      ]
    }
  }
}

OpenCode

Add to your .opencode.json MCP config:

{
  "mcp": {
    "garmin": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/garmin-mcp-server",
        "run",
        "garmin-mcp-server"
      ]
    }
  }
}

Any MCP Client

The server uses STDIO transport. Point your client at:

uv --directory /path/to/garmin-mcp-server run garmin-mcp-server

Example Conversations

Once connected, you can ask your AI assistant things like:

"How did I sleep last night?"
"Show me my runs from the past two weeks"
"What's my training readiness today?"
"Compare my resting heart rate over the last 7 days"
"Download the GPX file for my last bike ride"
"What are my race predictions for a half marathon?"
"How many steps have I averaged this month?"

Available Tools

Health Data

Tool	Description
`get_daily_summary`	Steps, distance, calories, floors climbed, active minutes for a date
`get_heart_rate`	Resting HR, min/max, heart rate zone breakdown
`get_sleep`	Sleep duration, stages (deep/light/REM/awake), sleep score
`get_stress`	All-day stress levels, average, duration by category
`get_body_battery`	Energy reserve levels throughout the day

Activities

Tool	Description
`get_recent_activities`	Most recent workouts with key metrics
`get_activities_by_date`	Activities in a date range, filterable by type (running, cycling, etc.)
`get_activity_details`	Full detail for a specific activity: pace, HR zones, elevation, training effect
`get_activity_splits`	Per-split/lap breakdown: pace, distance, HR, elevation

Body Composition

Tool	Description
`get_weight`	Weight measurements, BMI, body fat %
`get_body_composition`	Weight, body fat, muscle mass, bone mass, body water
`get_hydration`	Daily water intake and progress toward goal

Fitness Metrics

Tool	Description
`get_training_readiness`	Readiness score, HRV status, sleep quality, recovery time
`get_vo2max`	Estimated VO2 Max for running and cycling
`get_training_status`	Training load and status classification
`get_race_predictions`	Predicted times for 5K, 10K, half marathon, and marathon
`get_hrv`	Heart Rate Variability: status, weekly average, baseline
`get_endurance_score`	Aerobic fitness score over time

Export & Download

Tool	Description
`download_activity_fit`	Original FIT file (as ZIP) -- raw sensor data
`download_activity_gpx`	GPX track -- GPS coordinates for mapping
`download_activity_tcx`	TCX file -- GPS + HR + cadence
`download_activity_kml`	KML file -- for Google Earth
`download_activity_csv`	CSV file -- tabular data for spreadsheets

Additional Tools

Tool	Description
`get_devices`	Connected devices: model, firmware, battery, last sync
`get_daily_steps`	Step counts per day over a date range
`get_personal_records`	Personal bests across all activities
`get_respiration`	Breathing rate: waking, sleeping, high, low
`get_spo2`	Blood oxygen saturation readings
`get_goals`	Active fitness goals and current progress

Configuration

Environment Variable	Default	Description
`GARMIN_TOKEN_STORE`	`~/.garminconnect`	Directory where OAuth tokens are stored
`GARMIN_EXPORT_DIR`	`~/garmin-exports`	Directory for downloaded activity files

Development

Testing with MCP Inspector

uv run mcp dev src/garmin_mcp/server.py

This opens a web UI where you can invoke tools individually and inspect responses.

Project Structure

src/garmin_mcp/
├── server.py            # FastMCP server entry point
├── auth.py              # OAuth token management + garmin-mcp-setup CLI
└── tools/
    ├── health.py        # Daily health metrics
    ├── activities.py    # Workout listing and details
    ├── body.py          # Weight, body composition, hydration
    ├── fitness.py       # Training metrics, HRV, race predictions
    ├── devices.py       # Devices, steps, records, SpO2, goals
    └── export.py        # Activity file downloads

Important Notes

Unofficial API -- This uses undocumented Garmin Connect endpoints via python-garminconnect. Endpoints may change without warning.
Rate Limits -- Garmin enforces rate limits. Avoid rapid-fire requests; the AI assistant handles this gracefully with error messages.
Token Refresh -- The underlying garth library handles token refresh automatically. Tokens typically last ~1 year.
STDIO Safety -- The server never writes to stdout (which would corrupt the MCP transport). All logging goes to stderr.
No Interactive Auth -- The MCP server only uses pre-saved tokens. Run garmin-mcp-setup separately to authenticate.

License

MIT

Available Tools

29 tools

download_activity_csvA

Download a CSV file for a specific activity. Saves the CSV file and returns the file path. CSV files contain tabular activity data for spreadsheet analysis.

Inputs: activity_id (required). Returns: result

download_activity_fitA

Download a FIT file for a specific activity. Saves the original FIT file (as ZIP) and returns the file path. The FIT file contains the raw sensor data from the Garmin device.

Inputs: activity_id (required). Returns: result

download_activity_gpxA

Download a GPX file for a specific activity. Saves the GPX track file and returns the file path. GPX files contain GPS coordinates and are useful for mapping.

Inputs: activity_id (required). Returns: result

download_activity_kmlB

Download a KML file for a specific activity. Saves the KML file and returns the file path. KML files can be opened in Google Earth and similar tools.

Inputs: activity_id (required). Returns: result

download_activity_tcxA

Download a TCX file for a specific activity. Saves the TCX file and returns the file path. TCX files contain GPS + heart rate + cadence data.

Inputs: activity_id (required). Returns: result

get_activities_by_dateA

Get activities within a date range (YYYY-MM-DD). Optionally filter by activity type (running, cycling, swimming, etc.). Returns activity name, type, date, duration, distance, and key metrics.

Inputs: end_date (required), start_date (required), activity_type. Returns: result

get_activity_detailsB

Get detailed information for a specific activity by its ID. Returns comprehensive data including splits, HR zones, pace, elevation, etc.

Inputs: activity_id (required). Returns: result

get_activity_splitsA

Get split/lap data for a specific activity. Returns per-split pace, distance, elevation, heart rate.

Inputs: activity_id (required). Returns: result

get_body_batteryA

Get body battery data for a date (YYYY-MM-DD). Returns body battery levels showing energy reserves throughout the day.

Inputs: date (required). Returns: result

get_body_compositionA

Get body composition data for a date range (YYYY-MM-DD). Returns weight, body fat %, muscle mass, bone mass, body water %.

Inputs: start_date (required), end_date. Returns: result

get_daily_stepsA

Get daily step counts for a date range (YYYY-MM-DD). Returns step count per day, useful for trend analysis.

Inputs: end_date (required), start_date (required). Returns: result

get_daily_summaryB

Get daily activity summary for a date (YYYY-MM-DD). Returns steps, distance, calories, floors climbed, active minutes, and more.

Inputs: date (required). Returns: result

get_devicesA

Get information about connected Garmin devices. Returns device names, models, firmware versions, and last sync times.

Inputs: no named parameters. Returns: result

get_endurance_scoreB

Get endurance score for a date range (YYYY-MM-DD). Returns endurance score reflecting aerobic fitness over time.

Inputs: start_date (required), end_date. Returns: result

get_goalsA

Get active fitness goals. Returns current goals for steps, distance, calories, etc. and progress toward each.

Inputs: no named parameters. Returns: result

get_heart_rateB

Get heart rate data for a date (YYYY-MM-DD). Returns resting heart rate, min/max HR, and heart rate zones.

Inputs: date (required). Returns: result

get_hrvA

Get Heart Rate Variability (HRV) data for a date (YYYY-MM-DD). Returns HRV status, weekly average, and baseline.

Inputs: date (required). Returns: result

get_hydrationA

Get hydration data for a date (YYYY-MM-DD). Returns water intake in ml and progress toward daily goal.

Inputs: date (required). Returns: result

get_personal_recordsA

Get personal records (PRs) across all activities. Returns fastest times, longest distances, and other personal bests.

Inputs: no named parameters. Returns: result

get_race_predictionsA

Get race time predictions based on current fitness. Returns predicted times for 5K, 10K, half marathon, and marathon.

Inputs: no named parameters. Returns: result

get_recent_activitiesB

Get the most recent activities/workouts. Returns activity name, type, date, duration, distance, calories, and average HR.

Inputs: count. Returns: result

get_respirationA

Get respiration/breathing rate data for a date (YYYY-MM-DD). Returns breathing rate throughout the day.

Inputs: date (required). Returns: result

get_sleepA

Get sleep data for a date (YYYY-MM-DD). Returns sleep duration, sleep stages (deep, light, REM, awake), sleep score.

Inputs: date (required). Returns: result

get_spo2A

Get SpO2 (blood oxygen) data for a date (YYYY-MM-DD). Returns blood oxygen saturation readings.

Inputs: date (required). Returns: result

get_stressA

Get all-day stress data for a date (YYYY-MM-DD). Returns stress levels throughout the day, average stress, and stress duration breakdown.

Inputs: date (required). Returns: result

get_training_readinessA

Get training readiness score for a date (YYYY-MM-DD). Returns readiness score, HRV status, sleep quality, recovery time, and training load.

Inputs: date (required). Returns: result

get_training_statusB

Get training status for a date (YYYY-MM-DD). Returns training load, training effect, and training status classification.

Inputs: date (required). Returns: result

get_vo2maxA

Get VO2 Max / max metrics data for a date (YYYY-MM-DD). Returns estimated VO2 Max for running and cycling.

Inputs: date (required). Returns: result

get_weightA

Get weight/weigh-in data for a date range (YYYY-MM-DD). Returns weight measurements, BMI, body fat percentage if available.

Inputs: start_date (required), end_date. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored 2026-08-30 12:45 across 29 tools

Disambiguation4/5

Most tools map to distinct Garmin data categories, but a few boundaries are fuzzy: get_weight and get_body_composition overlap on weight and body fat, and get_daily_summary overlaps with get_daily_steps and get_heart_rate on daily metrics. Still, an agent can usually select the right tool from the descriptions.

Naming Consistency5/5

The naming follows a consistent verb_noun pattern: get_* for data retrieval and download_activity_* for file exports. Plural/singular variations are minor and do not affect predictability.

Tool Count2/5

29 tools is excessive for a Garmin data server. Many could be consolidated, such as the five download_activity_format tools into a single exporter, and get_weight/get_body_composition into one body metrics tool. The broad scope helps justify the number, but the surface still feels over-split.

Completeness4/5

The server covers a comprehensive read-only Garmin domain: activities, daily summaries, body metrics, health metrics, training readiness, sleep, stress, devices, and file downloads. Minor gaps exist, such as lacking date-range endpoints for some metrics (e.g., sleep, stress) and no way to search activities beyond recent/date-based retrieval.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Coach Icarus
io.github.simkessy
Adaptive running coach MCP server — training data, plans, and recovery for AI assistants.
Fitness Tracking Health & Wellness
1
https://api.coachicarus.com/mcp
garmlink
ai.garmlink
Garmin watch data for AI assistants: activities, sleep, HRV, recovery. Never writes to Garmin.
1
https://api.garmlink.ai/mcp
Fitness AI Connector
io.github.fmp-projects
Garmin data in Claude & ChatGPT via the Garmin Health API. OAuth sign-in, no password sharing.
Health & Wellness Fitness Tracking
29
https://garmin-mcp-nuqd.onrender.com/mcp
Garmin MCP by geekist.coB
io.github.theGeekist
Explore Garmin activity and health data with your AI assistant.
Fitness Tracking Health & Wellness
511
https://garmin.geekist.co/mcp

Related MCP Servers

claude-garmin
Health & Wellness Fitness Tracking Sports
Jack-Abyss
A
license
Not graded
quality
C
maintenance
MCP server that connects Garmin Connect data to Claude, enabling training analysis, recovery checks, and personalized plans based on real metrics like HRV, training load, and activities.
Updated a month ago (2026-09-29 16:39 UTC)
24
MIT
garth-mcp-server
Health & Wellness Fitness Tracking
matin
A
license
Not graded
quality
D
maintenance
MCP server to interact with Garmin Connect, enabling retrieval of health, activity, and device data through natural language.
Updated 9 months ago (2026-02-01 22:20 UTC)
66
MIT
garmin-mcp
Health & Wellness Fitness Tracking
aayush-lunawat
A
license
Not graded
quality
D
maintenance
A local MCP server that exposes your Garmin Connect data—sleep, HRV, training readiness, workouts, and more—to any MCP-compatible AI assistant. Runs entirely on your machine and keeps your Garmin credentials private.
Updated 3 months ago (2026-08-07 17:35 UTC)
MIT
mcp-garmin-connect
Health & Wellness Fitness Tracking
kavakoss
A
license
B
quality
B
maintenance
An MCP server that gives LLMs access to Garmin Connect data, including training, recovery, sleep, stress, VO2 Max, and running summaries for personalized fitness advice.
Updated 16 days ago (2026-10-27 18:16 UTC)
24
42 PyPI
1
MIT

Garmin Connect MCP Server

Features

Quick Start

Prerequisites

1. Clone and install

2. Authenticate with Garmin

3. Connect to your AI assistant

Claude Desktop

OpenCode

Any MCP Client

Example Conversations

Available Tools

Health Data

Activities

Body Composition

Fitness Metrics

Export & Download

Additional Tools

Configuration

Development

Testing with MCP Inspector

Project Structure

Important Notes

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

claude-garmin

garth-mcp-server

garmin-mcp

mcp-garmin-connect