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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.