garmin-connect-mcp
An MCP server for Garmin Connect that provides access to fitness activities, health statistics, and sleep data by routing requests through a headless browser to bypass API restrictions. It enables users to query detailed metrics like heart rate zones, body battery, and GPS tracks using any MCP-compatible client.
README
garmin-connect-mcp
MCP server for Garmin Connect. Access your activities, health stats, sleep data, FIT files, and more from Claude Code or any MCP client.
Why This Exists
In March 2026, Garmin changed their authentication API, breaking garth and python-garminconnect — the two most popular libraries for accessing Garmin data programmatically. Garth has been officially deprecated. Garmin added Cloudflare TLS fingerprinting that blocks all non-browser HTTP clients (Node.js fetch, Python requests, curl) from their API endpoints.
This project works around that by routing all API calls through a headless Playwright browser, inheriting a real Chrome TLS fingerprint. Authentication uses browser cookies captured from a manual login session.
Install
npm install -g @etweisberg/garmin-connect-mcp
npx playwright install chromium
Then register with Claude Code:
claude mcp add garmin -- npx @etweisberg/garmin-connect-mcp
You also need the Playwright MCP server for the login flow:
claude mcp add playwright -- npx @playwright/mcp@latest
Prerequisites
- Node.js 18+
- Playwright MCP server (for browser-based login)
- A Garmin Connect account with a synced device
Setup
1. Login
In Claude Code, call the garmin-login tool. It will walk you through:
- Opening Garmin Connect in the Playwright browser
- Logging in manually
- Extracting cookies and CSRF token
- Saving the session to
~/.garmin-connect-mcp/session.json
2. Verify
Call the check-session tool to confirm authentication works.
Session cookies expire after a few hours. Re-run the login flow when they do.
Available Tools
Session & Auth
| Tool | Description |
|---|---|
garmin-login |
Returns login instructions for the Playwright MCP browser |
check-session |
Validates the saved session is still active |
run-tests |
Returns a test plan to verify all tools work |
Activities
| Tool | Description |
|---|---|
list-activities |
List activities with pagination |
get-activity |
Full activity summary (distance, duration, HR, calories) |
get-activity-details |
Time-series metrics (HR, cadence, elevation over time) |
get-activity-splits |
Lap/split data |
get-activity-hr-zones |
Heart rate time-in-zone breakdown |
get-activity-polyline |
Full-resolution GPS track |
get-activity-weather |
Weather conditions during activity |
download-fit |
Download original FIT file |
Daily Health
| Tool | Description |
|---|---|
get-daily-summary |
Steps, calories, distance, intensity minutes |
get-daily-heart-rate |
Heart rate data throughout the day |
get-daily-stress |
Stress levels throughout the day |
get-daily-summary-chart |
Combined wellness chart data |
get-daily-intensity-minutes |
Intensity minutes for a date |
get-daily-movement |
Movement/activity data |
get-daily-respiration |
Respiration rate data |
Sleep / Body Battery / HRV
| Tool | Description |
|---|---|
get-sleep |
Sleep score, duration, stages, SpO2 |
get-body-battery |
Body battery charged/drained values |
get-hrv |
Heart rate variability data |
Training & Recovery
| Tool | Description |
|---|---|
get-training-readiness |
Training readiness score (sleep, recovery, load) |
get-sleep-stats |
Sleep statistics over a date range |
get-hydration |
Daily hydration/water intake data |
Weight / Records / Fitness
| Tool | Description |
|---|---|
get-weight |
Weight measurements over a date range |
get-personal-records |
All personal records with history |
get-fitness-stats |
Aggregated activity stats by type |
get-vo2max |
Latest VO2 Max estimate |
get-hr-zones-config |
Heart rate zone boundaries |
get-power-zones |
Power zone config for all sports |
get-user-profile |
User profile and settings |
Calendar, Goals & Badges
| Tool | Description |
|---|---|
get-calendar |
Monthly calendar with activities and events |
get-goals |
Active, future, or past fitness goals |
get-badges |
All earned badges/achievements |
get-badge-leaderboard |
Badge leaderboard among connections |
Workouts
| Tool | Description |
|---|---|
list-workouts |
List saved workouts |
get-workout |
Get workout details (steps, segments) |
create-workout |
Create a new workout (warmup, intervals, cooldown) |
schedule-workout |
Schedule a workout to a date (syncs to device) |
delete-workout |
Delete a workout |
download-workout-fit |
Download a workout as a FIT file |
Architecture
Claude Code / MCP Client
|
| MCP (stdio)
v
garmin-connect-mcp server
|
| page.evaluate(fetch(...))
v
Headless Playwright Chromium
|
| HTTPS (real Chrome TLS fingerprint)
v
connect.garmin.com/gc-api/*
All API calls are made from within a headless Chromium browser context via page.evaluate(fetch(...)). This inherits the real Chrome TLS fingerprint, bypassing Cloudflare's detection of non-browser clients.
Auth flow: Cookies + CSRF token are captured from a manual browser login (via the Playwright MCP server) and stored at ~/.garmin-connect-mcp/session.json. The headless browser loads these cookies on startup.
Why not direct HTTP? Cloudflare blocks Node.js fetch, Python requests, and even curl with a 403. Only requests from a real browser TLS stack are accepted.
Development
git clone https://github.com/etweisberg/garmin-connect-mcp.git
cd garmin-connect-mcp
npm install
npx playwright install chromium
npm run build
Scripts
| Command | Description |
|---|---|
npm run build |
Compile TypeScript |
npm run lint |
Run ESLint |
npm run format |
Format with Prettier |
npm run typecheck |
Type check without emitting |
npm test |
Run integration tests (requires valid session) |
Local Integration Testing
The standalone test suite (npm test) requires a valid Garmin session and hits the real API. Run it locally after authenticating:
npm test
Contributing
- Create a feature branch off
main - Make your changes
- Run checks:
npm run lint npm run format npm run typecheck npm run build - Test via Claude Code: The recommended way to verify your changes is through Claude Code. After building, call the
run-testsMCP tool — it returns a test plan that exercises all 27 tools against the live Garmin API. Tell Claude to execute the plan and report results. - Open a PR against
main
CI runs lint, format check, typecheck, and build on every PR. Integration tests run locally only (they require Garmin authentication that can't safely run in CI).
Releasing
Releases are fully automated. Every merge to main triggers the release workflow which:
- Runs CI (lint, format, typecheck, build)
- Bumps the patch version
- Publishes to npm with provenance
- Creates a GitHub Release
No manual version bumping or tagging needed — just merge your PR.
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。