Skip to main content

Garmin Workouts MCP Server

Project description

Garmin Workouts MCP Server

An MCP server that allows you to create, list, and manage Garmin Connect workouts using natural language descriptions through MCP-compatible clients.

Features

  • Create workouts: Generate structured Garmin workouts from natural language descriptions using AI
  • List workouts: View all your existing workouts on Garmin Connect
  • Get workout details: Retrieve detailed information about specific workouts
  • MCP Integration: Works with any MCP-compatible client (Claude Desktop, etc.)

Setup

  1. Install and run using uvx:
uvx garmin-workouts-mcp
  1. Configure in your MCP client (e.g., Claude Desktop):

Add to your MCP client configuration:

{
  "mcpServers": {
    "garmin-workouts": {
      "command": "uvx",
      "args": ["garmin-workouts-mcp"]
    }
  }
}

On first use, you'll be prompted to login to Garmin Connect. Upon successful login, access and refresh tokens will be stored locally for subsequent calls.

Usage

This server provides the following MCP tools that can be used through any MCP-compatible client:

Generate Workout Data Prompt

Use the generate_workout_data_prompt tool to create a prompt for an LLM to generate structured workout data:

generate_workout_data_prompt("10 min warmup, 5x(1km at 4:30 pace, 2min recovery), 10 min cooldown")

Upload Workout

Use the upload_workout tool to upload structured workout data to Garmin Connect:

upload_workout(workout_data_json)

List Workouts

list_workouts()

Get Workout Details

get_workout("workout_id_here")

The tool supports various workout types:

  • Running: pace targets, distance/time based intervals
  • Cycling: power, cadence, speed targets
  • Swimming: time/distance based sets
  • Strength training: circuit-style workouts
  • General cardio: heart rate based training

Workout Description Examples

  • "30min easy run at conversational pace"
  • "5km tempo run at 4:15 min/km pace"
  • "10 min warmup, 3x(20min at 280w, 5min at 150w), 10min cooldown"
  • "Swimming: 400m warmup, 8x(50m sprint, 30s rest), 400m cooldown"
  • "Strength circuit: 5x(30s pushups, 30s squats, 30s plank, 60s rest)"

Environment Variables

  • GARTH_HOME: Custom location for Garmin credentials (optional, defaults to ~/.garth)

Credits

This project incorporates ideas and prompt designs inspired by openai-garmin-workout, which is licensed under the MIT License.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

garmin_workouts_mcp-0.3.0.tar.gz (10.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

garmin_workouts_mcp-0.3.0-py3-none-any.whl (10.2 kB view details)

Uploaded Python 3

File details

Details for the file garmin_workouts_mcp-0.3.0.tar.gz.

File metadata

  • Download URL: garmin_workouts_mcp-0.3.0.tar.gz
  • Upload date:
  • Size: 10.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.5

File hashes

Hashes for garmin_workouts_mcp-0.3.0.tar.gz
Algorithm Hash digest
SHA256 06cd0dd758f253c063b51bbe433ea5fc287ba05380c796a82f7858f7a3ba4c34
MD5 8fa0262455155f4307af044d733aa914
BLAKE2b-256 91df3160f0d5bedecd82b248b8a5814cb162dd66af54f180375995da4ef08328

See more details on using hashes here.

File details

Details for the file garmin_workouts_mcp-0.3.0-py3-none-any.whl.

File metadata

File hashes

Hashes for garmin_workouts_mcp-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 44e7f3951d47a4ef2c4627704e6b38273c0fb39af8125d33959691b7628f3d1d
MD5 f19e8aa508cada05ce947404b17c54cc
BLAKE2b-256 ee69ba134ad3125338849c351991018ae916ae7fdd5696f3606adb61c1b79ceb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page