About Garmin Connect Personal API
Garmin Connect Personal API MCP is a read-only server that lets AI assistants access personal Garmin Connect training, recovery and health data. It can run locally or on the user's Cloudflare account, and provides detailed activity, sleep and wellness records.
Key features
- 01Read-only Garmin Connect data access
- 02Activity details, streams and laps
- 03Sleep and HRV records
- 04Daily recovery and health summaries
- 05Weight, hydration and food logs
- 06Wellness and cycle data
Use cases
- 01Review training activities and workout metrics
- 02Track sleep and HRV across a date range
- 03Inspect daily recovery and heart-rate data
- 04Review hydration, nutrition or cycle records
MCP support
Exposes read-only Garmin Connect Personal API data through MCP tools. It can run locally or be hosted on Cloudflare for remote MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @hannta/garmin-connect-personal-api-mcpGARMIN_PERSONAL_API_KEYSecretGarmin Connect Personal API key (optional: the auth command saves one instead)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
27Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| date | string | No | Calendar date, YYYY-MM-DD. Default: today in the user's time zone. |
Details
From the project READMEGarmin Connect Personal API MCP
Not affiliated with or endorsed by Garmin. Garmin and Garmin Connect are trademarks of Garmin Ltd.
A read-only MCP server that gives AI assistants your own Garmin Connect training, recovery and health data through the official Garmin Connect Personal API. Run it on your own computer, or host it on your own Cloudflare account to use it from anywhere.
AI agents: to set this up for a user, follow docs/AGENT-SETUP.md.
Setup
You need a Garmin Connect Personal API key, which you create in Garmin Connect on the web.
Run locally
The quickest way, for Claude Code, Claude Desktop, Cursor, VS Code and other clients that run local servers. Needs Node.js 22+.
Paste this into your coding agent:
Connect @hannta/garmin-connect-personal-api-mcp
Or do it yourself: docs/LOCAL.md.
Host on Cloudflare
For Claude on the web and on mobile, and any other client that connects to remote servers with OAuth. The free plan is enough, apart from one known limitation.
-
One click:
-
Manual: follow docs/DEPLOY.md.
Then connect your MCP client, such as Claude, ChatGPT, Cursor or VS Code.
Tools
| Tool | What it returns |
|---|---|
garmin_get_day | One day at a glance: sleep, HRV, Body Battery, stress, resting HR, intensity minutes, activities |
garmin_get_days | The same over a date range, one row per day, with daily activity totals and training load |
garmin_search_activities | Activities in a date range with Garmin IDs and fastest splits, or totals per week |
garmin_get_activity | One activity in depth: pace, HR zones, running dynamics, power, training effect, interval totals, strength sets per exercise |
garmin_get_activity_streams | One activity's time series (HR, pace, grade-adjusted pace, cadence, power, elevation, …) |
garmin_get_activity_laps | One row per lap and interval rep, from the activity's FIT file |
garmin_get_sleep | One night's sleep in detail: score components with optimal ranges, sleep need and why it changed, naps |
garmin_get_sleep_summaries | Sleep per night over a date range |
garmin_get_hrv | One night's HRV with baseline, status and overnight readings |
garmin_get_hrv_summaries | HRV per night over a date range |
garmin_get_daily_summaries | Resting HR, Body Battery, stress, intensity minutes, steps per day over a date range |
garmin_get_weight | Weigh-ins and body composition over a date range |
garmin_get_profile | Profile settings and heart-rate zones |
garmin_get_body_battery | Body Battery per day: charged, drained and the sleep / activity events behind it |
garmin_get_stress | Stress per day: average level and minutes at rest / low / medium / high |
garmin_get_steps | Steps per day with goal and distance |
garmin_get_heart_rate | One day's resting / min / max heart rate, optionally averaged per 15 minutes |
garmin_get_spo2 | One day's blood oxygen (Pulse Ox), optionally hourly with altitude |
garmin_get_fitness_age | Fitness age and its components (resting HR, BMI, vigorous days / minutes) |
garmin_get_heart_rate_zones | Heart-rate zones per sport |
garmin_get_weight_goals | Weight goals in effect (target kg) |
garmin_get_activity_workouts | The structured workout an activity followed: steps, targets (HR, pace, power) and repeats |
garmin_get_hydration | Hydration per day: intake, goal, sweat loss (ml) |
garmin_get_food_log | One day's food log: calories and macros eaten vs. goals, per meal and food |
garmin_get_wellness_activities | Wellness sessions (e.g. Health Snapshot, breathwork) with HR, stress, HRV, SpO2 |
garmin_get_menstrual_cycle | Cycle day, period and fertile window, predictions and cycle analysis |
garmin_get_menstrual_day | One day's logged flow, symptoms and moods, with that day's cycle summary |
Good to know
- Range tools default to the last 7 days. If a range is too long for one Garmin request, the error says the maximum and the assistant splits it into several calls.
- Output is metric, with the unit in every field name. Dates are
YYYY-MM-DDin your time zone; sleep and HRV are keyed by the wake-up date. - Location, sexual activity and sex drive data are never returned.
- Known limitation:
garmin_get_activity_lapscan fail on long activities on the Cloudflare free plan. See Known limitations.
Development
Requires Node.js 24+.
npm install
cp .dev.vars.example .dev.vars # then add GARMIN_API_KEY and OWNER_PASSPHRASE
npm run check # typecheck, lint, format check, tests
npm run today # print today's recovery data using your key
npm run dev # MCP server at http://localhost:8787/mcp
npm run build # local server in dist/cli.mjs
To try the local server, connect the
MCP Inspector to it and sign in with
OWNER_PASSPHRASE.
Architecture and conventions: docs/DEVELOPMENT.md.
License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.