Skip to content
Back to search

garmin-connect-mcp

MCP server for Garmin Connect — access 61 health, fitness and activity tools from any AI assistant

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nicolasvegam--garmin-connect-mcp/badge.svg)](/listings/nicolasvegam--garmin-connect-mcp)

HTML

<a href="/listings/nicolasvegam--garmin-connect-mcp"><img src="/api/listings/nicolasvegam--garmin-connect-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Claude Code

claude mcp add garmin -e GARMIN_EMAIL=you@email.com -e GARMIN_PASSWORD=yourpass -- npx -y @nicolasvegam/garmin-connect-mcp

Claude Desktop

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

{
  "mcpServers": {
    "garmin": {
      "command": "npx",
      "args": ["-y", "@nicolasvegam/garmin-connect-mcp"],
      "env": {
        "GARMIN_EMAIL": "you@email.com",
        "GARMIN_PASSWORD": "yourpass"
      }
    }
  }
}

Cursor

Add to `.cursor/mcp.json` in your project root:

{
  "mcpServers": {
    "garmin": {
      "command": "npx",
      "args": ["-y", "@nicolasvegam/garmin-connect-mcp"],
      "env": {
        "GARMIN_EMAIL": "you@email.com",
        "GARMIN_PASSWORD": "yourpass"
      }
    }
  }
}

Windsurf

Add to `~/.codeium/windsurf/mcp_config.json`:

{
  "mcpServers": {
    "garmin": {
      "command": "npx",
      "args": ["-y", "@nicolasvegam/garmin-connect-mcp"],
      "env": {
        "GARMIN_EMAIL": "you@email.com",
        "GARMIN_PASSWORD": "yourpass"
      }
    }
  }
}

Any MCP Client

Run the server with environment variables:

GARMIN_EMAIL=you@email.com GARMIN_PASSWORD=yourpass npx -y @nicolasvegam/garmin-connect-mcp

The server communicates over stdio using the [Model Context Protocol](https://modelcontextprotocol.io/).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 227 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # garmin-connect-mcp
  2. MCP server for Garmin Connect. Access your fitness, health, and training data from Claude Code, Claude Desktop, Cursor, Windsurf, or any MCP client.
  3. **61 tools** across 7 categories: activities, daily health, trends, sleep, body composition, performance/training, and profile/devices.
  4. API endpoints and authentication flow based on [`python-garminconnect`](https://github.com/cyberjunky/python-garminconnect) by [cyberjunky](https://github.com/cyberjunky).
  5. ## Requirements
  6. - Node.js 20+
  7. - A Garmin Connect account (email and password)
  8. ## Installation
  9. ### Claude Code
  10. ```bash
  11. claude mcp add garmin -e GARMIN_EMAIL=you@email.com -e GARMIN_PASSWORD=yourpass -- npx -y @nicolasvegam/garmin-connect-mcp
  12. ```
  13. ### Claude Desktop
  14. Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):
  15. ```json
  16. {
  17. "mcpServers": {
  18. "garmin": {
  19. "command": "npx",
  20. "args": ["-y", "@nicolasvegam/garmin-connect-mcp"],
  21. "env": {
  22. "GARMIN_EMAIL": "you@email.com",
  23. "GARMIN_PASSWORD": "yourpass"
  24. }
  25. }
  26. }
  27. }
  28. ```
  29. ### Cursor
  30. Add to `.cursor/mcp.json` in your project root:
  31. ```json
  32. {
  33. "mcpServers": {
  34. "garmin": {
  35. "command": "npx",
  36. "args": ["-y", "@nicolasvegam/garmin-connect-mcp"],
  37. "env": {
  38. "GARMIN_EMAIL": "you@email.com",
  39. "GARMIN_PASSWORD": "yourpass"
  40. }
  41. }
  42. }
  43. }
  44. ```
  45. ### Windsurf
  46. Add to `~/.codeium/windsurf/mcp_config.json`:
  47. ```json
  48. {
  49. "mcpServers": {
  50. "garmin": {
  51. "command": "npx",
  52. "args": ["-y", "@nicolasvegam/garmin-connect-mcp"],
  53. "env": {
  54. "GARMIN_EMAIL": "you@email.com",
  55. "GARMIN_PASSWORD": "yourpass"
  56. }
  57. }
  58. }
  59. }
  60. ```
  61. ### Any MCP Client
  62. Run the server with environment variables:
  63. ```bash
  64. GARMIN_EMAIL=you@email.com GARMIN_PASSWORD=yourpass npx -y @nicolasvegam/garmin-connect-mcp
  65. ```
  66. The server communicates over stdio using the [Model Context Protocol](https://modelcontextprotocol.io/).
  67. ## Available Tools
  68. ### Activities (12 tools)
  69. | Tool | Description |
  70. |------|-------------|
  71. | `get_activities` | List recent activities with pagination |
  72. | `get_activities_by_date` | Search activities within a date range |
  73. | `get_last_activity` | Get the most recent activity |
  74. | `count_activities` | Get total number of activities |
  75. | `get_activity` | Summary data for a specific activity |
  76. | `get_activity_details` | Detailed metrics: HR, pace, elevation time series |
  77. | `get_activity_splits` | Per-km or per-mile split data |
  78. | `get_activity_weather` | Weather conditions during activity |
  79. | `get_activity_hr_zones` | Time in each heart rate zone |
  80. | `get_activity_exercise_sets` | Strength training sets (reps, weight) |
  81. | `get_activity_types` | All available activity types |
  82. | `get_progress_summary` | Fitness stats over a date range by activity type |
  83. ### Daily Health (14 tools)
  84. | Tool | Description |
  85. |------|-------------|
  86. | `get_daily_summary` | Full daily summary (steps, calories, distance, etc.) |
  87. | `get_steps` | Step count for a date |
  88. | `get_steps_chart` | Intraday step data throughout the day |
  89. | `get_heart_rate` | Heart rate data (resting, max, zones, time series) |
  90. | `get_resting_heart_rate` | Resting heart rate for a date |
  91. | `get_stress` | Stress levels and time series |
  92. | `get_body_battery` | Body Battery energy levels (date range) |
  93. | `get_body_battery_events` | Battery charge/drain events for a day |
  94. | `get_respiration` | Breathing rate data |
  95. | `get_spo2` | Blood oxygen saturation |
  96. | `get_intensity_minutes` | Moderate/vigorous intensity minutes |
  97. | `get_floors` | Floors climbed chart data |
  98. | `get_hydration` | Daily hydration/water intake |
  99. | `get_daily_events` | Daily wellness events |
  100. ### Trends (4 tools)
  101. | Tool | Description |
  102. |------|-------------|
  103. | `get_daily_steps_range` | Daily step counts over a date range |
  104. | `get_weekly_steps` | Weekly step aggregates |
  105. | `get_weekly_stress` | Weekly stress aggregates |
  106. | `get_weekly_intensity_minutes` | Weekly intensity minutes |
  107. ### Sleep (2 tools)
  108. | Tool | Description |
  109. |------|-------------|
  110. | `get_sleep_data` | Sleep stages, score, bed/wake times |
  111. | `get_sleep_data_raw` | Raw sleep data with HR and SpO2 |
  112. ### Body Composition (5 tools)
  113. | Tool | Description |
  114. |------|-------------|
  115. | `get_body_composition` | Weight, BMI, body fat %, muscle mass (date range) |
  116. | `get_latest_weight` | Most recent weight entry |
  117. | `get_daily_weigh_ins` | All weigh-ins for a date |
  118. | `get_weigh_ins` | Weigh-in records over a date range |
  119. | `get_blood_pressure` | Blood pressure readings (date range) |
  120. ### Performance & Training (11 tools)
  121. | Tool | Description |
  122. |------|-------------|
  123. | `get_vo2max` | VO2 Max estimate (running/cycling) |
  124. | `get_training_readiness` | Training Readiness score |
  125. | `get_training_status` | Training status and load |
  126. | `get_hrv` | Heart Rate Variability |
  127. | `get_endurance_score` | Endurance fitness score |
  128. | `get_hill_score` | Climbing performance score |
  129. | `get_race_predictions` | 5K/10K/half/full marathon predictions |
  130. | `get_fitness_age` | Estimated fitness age |
  131. | `get_personal_records` | All personal records |
  132. | `get_lactate_threshold` | Lactate threshold HR and pace |
  133. | `get_cycling_ftp` | Functional Threshold Power (cycling) |
  134. ### Profile & Devices (13 tools)
  135. | Tool | Description |
  136. |------|-------------|
  137. | `get_user_profile` | User social profile and preferences |
  138. | `get_user_settings` | User settings, measurement system, sleep schedule |
  139. | `get_devices` | Registered Garmin devices |
  140. | `get_device_settings` | Settings for a specific device |
  141. | `get_device_last_used` | Last used device info |
  142. | `get_primary_training_device` | Primary training device |
  143. | `get_device_solar_data` | Solar charging data |
  144. | `get_gear` | All tracked gear/equipment |
  145. | `get_gear_stats` | Usage stats for a gear item |
  146. | `get_goals` | Active goals and progress |
  147. | `get_earned_badges` | Earned badges and achievements |
  148. | `get_workouts` | Saved workouts |
  149. | `get_workout` | Specific workout by ID |
  150. ## Authentication
  151. Uses Garmin Connect credentials (email/password) via environment variables. OAuth tokens are cached in `~/.garmin-mcp/` to avoid re-authentication on each request.
  152. ### MFA (Multi-Factor Authentication)
  153. If your Garmin account has MFA enabled (required for devices with ECG capabilities), you need to run the interactive setup once before using the MCP server:
  154. ```bash
  155. GARMIN_EMAIL='you@email.com' GARMIN_PASSWORD='yourpass' npx -y @nicolasvegam/garmin-connect-mcp setup
  156. ```
  157. The same flow is available as its own executable, `garmin-connect-mcp-setup`:
  158. ```bash
  159. GARMIN_EMAIL='you@email.com' GARMIN_PASSWORD='yourpass' npx -y --package @nicolasvegam/garmin-connect-mcp garmin-connect-mcp-setup
  160. ```
  161. This will:
  162. 1. Log in to Garmin Connect
  163. 2. Prompt you for the MFA code sent to your email or authenticator app (the setup command asks for the code on the terminal; the MCP server itself cannot)
  164. 3. Save OAuth tokens to `~/.garmin-mcp/`
  165. After setup, the MCP server will use the saved tokens automatically — no MFA prompt needed until the tokens expire. When they do, simply run the setup command again.
  166. ## Development
  167. ```bash
  168. git clone https://github.com/Nicolasvegam/garmin-connect-mcp.git
  169. cd garmin-connect-mcp
  170. npm install
  171. npm run build
  172. npm test
  173. ```
  174. To test locally:
  175. ```bash
  176. GARMIN_EMAIL=you@email.com GARMIN_PASSWORD=yourpass npm start
  177. ```
  178. ## Credits
  179. - API endpoints and authentication flow based on [`python-garminconnect`](https://github.com/cyberjunky/python-garminconnect) by [cyberjunky](https://github.com/cyberjunky)
  180. ## License
  181. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.