Skip to main content
Glama
Sign In
Garmin MCP

Garmin MCP

by endurancetools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Garmin MCP

npm CI MCP registry

Ask your AI assistant how your training is really going. Garmin MCP is an unofficial, open-source MCP server for your Garmin Connect data: training load, form and morning readiness computed on your machine with methods from published sports-science literature, with citations; 21 tools designed around the questions athletes ask, not a mirror of Garmin's API; a local SQLite cache that downloads only what a question needs; and structured workouts that go from the answer to your Garmin calendar and watch. It also reads activities, health, sleep, training status, body composition, gear, devices and the workout library.

Works with Claude Code, Claude Desktop, Codex, Antigravity CLI, opencode and any other MCP client (stdio or streamable HTTP).

Documentation: endurancetools.github.io/garmin-mcp (getting started per client, what to ask, configuration, troubleshooting). Contributing and development: DEVELOPMENT.md.

Unofficial. Garmin and Garmin Connect are trademarks of Garmin Ltd. or its subsidiaries; this project is not affiliated with or endorsed by Garmin. The training analytics (get_load, get_readiness) are training information, not medical advice.

Why Garmin MCP

  • Answers you can check. Training load (TSS from power, pace, heart rate or session RPE), fitness, fatigue and form (CTL/ATL/TSB), ACWR, intensity distribution and morning readiness from your own HRV, resting heart rate, sleep and load against your own baselines, with methods from published sports-science literature, with citations. Every answer returns the values and rules it used, and you can change them. Methods and evidence

  • Designed tools, not an API mirror. 21 tools built around questions like "review my week" or "can I train hard today?", so one call answers one question. The whole tool list costs the model about 8,600 tokens of context, and the first tool call was the right one in 48 of 48 tool-selection scenarios. Designed tools

  • Local and private. You sign in on Garmin's own page, so your password never passes through the tool. What it downloads stays in a local database on your computer, answers come back from it in milliseconds, downloads are paced to stay gentle with Garmin, and tool answers go only to the AI client you connect. What is stored where

  • From answer to watch. Ask for "6×400 m with 90 s rest on Thursday": you see the steps and estimated duration first, nothing is saved until you agree, and then it goes to your Garmin calendar and syncs to the watch. Workouts and calendar

Related MCP server: garmin-mcp

Getting started

Requirements: Node.js 22 or newer, a Garmin Connect account, and Chrome, Edge, Brave or Chromium for the sign-in window (there is a terminal fallback).

1. Sign in once. This opens Garmin's own sign-in page in your browser. Your password never passes through the tool; only the tokens Garmin issues are stored, in ~/.garmin-mcp.

npx -y garmin-mcp-cli login

2. Add the server to your client.

Client

Configuration

Claude Code

claude mcp add garmin -- npx -y garmin-mcp-server

Claude Desktop

install garmin-mcp-<version>.mcpb from the GitHub release, or add to claude_desktop_config.json: {"mcpServers":{"garmin":{"command":"npx","args":["-y","garmin-mcp-server"]}}}

Codex

~/.codex/config.toml: [mcp_servers.garmin] command = "npx" args = ["-y", "garmin-mcp-server"]

Antigravity CLI

agy mcp add garmin npx -y garmin-mcp-server

opencode

opencode.json: {"mcp":{"garmin":{"type":"local","command":["npx","-y","garmin-mcp-server"],"enabled":true}}}

Any other client

command npx, arguments -y garmin-mcp-server, transport stdio

3. Ask. Nothing is downloaded until a question needs it. For example:

  • "How did I sleep this week?" or "How did my HRV trend over the summer?"

  • "Review my training week" or "Summarise my block from 2026-08-04 to 2026-09-28"

  • "Am I fatigued? What is my form right now?"

  • "When is my next race?" or "What is planned this week?"

  • "Build me 6×400 m with 90 s rest for Thursday" (you see the steps first, nothing is saved until you agree)

  • "Rename activity 21001 to Parkrun PB"

Optional: pre-load a range so the first questions answer instantly.

npx -y garmin-mcp-cli sync --scope all --from 2026-07-01 --to 2026-09-30

How it fetches data

Logging in and starting the server download nothing. When a question needs days that are not in the local database, the tool downloads exactly that range, waits up to 20 s and answers; anything left keeps downloading in the background and the answer says so (meta.source is partial). Everything downloaded stays in the local database: stored days are never downloaded again unless you pass --force, so repeating a question costs nothing.

To stay gentle with Garmin, long ranges go in 7-day chunks, newest first, with a random 1-11 s pause after each chunk that actually downloaded something, at most 600 requests per day. A 429 or a Cloudflare challenge pauses all downloads for 6 h. An interrupted sync continues where it left off.

With GARMIN_AUTO_FETCH=false nothing is downloaded unless you run garmin sync or the garmin_sync tool; read tools then return the missing range in meta.sync_hint and the model asks you first.

Measured on a real account after a 90-day sync (433 requests in about an hour): answers come from the local database in 1-110 ms.

Tools

Tool

Purpose

get_activities

dense activity list with cursor paging (GAP, cadence, NP, Training Effect label, temperature when downloaded); type takes a Garmin type key (all keys in garmin://activity-types), plus name, min_duration_min/max_duration_min and a pace range

get_activity

one activity: summary (with running dynamics, breathing, stamina, HR source), splits (laps with dynamics and workout steps), hr_zones, power_zones, weather, exercise_sets (strength sets), stream_summary (stream per km, 5 min, half or quarter), or full (all sections plus the raw stream, 50 KB pages, optional metrics and downsample_s)

update_activity

name, type, description, RPE, feel

download_activity_file

FIT (unzipped), GPX, TCX, KML, CSV to the download directory (GARMIN_FIT_DOWNLOAD_DIR)

query_health

steps (with daily distance), resting HR (with daily min/max HR), HRV (with status and baseline), sleep, stress, body battery, respiration, SpO2, intensity minutes, calories (burned, and eaten when a food log is linked), floors; per day or week, with 7/28-day trends

get_sleep

one night with stages, or a range with averages

get_training_status

VO2max, readiness, recovery time, Garmin status, load and load focus, garmin_load_model (CTL/ATL/TSB from Garmin's training load, optionally the daily series); race predictions, endurance/hill score, fitness age, personal records, acclimation

get_body_composition

weigh-ins in kg with trend

get_period_summary

week, month or any from..to range up to 366 days: volume per sport, HR zones, rest days, longest/hardest, garmin_load_model at the end, health and energy averages

list_workouts, get_workout

workout library, scheduled workouts, races and events from the calendar in any date range (default: next 60 days), readable steps

create_workout, schedule_workouts

workouts from presets (run intervals, walk/run, easy Z2, strength circuit) or a typed definition (nestable repeats, HR/pace/power targets); create_workout with dry_run: true shows the steps and estimated duration without saving; schedule_workouts puts workouts on the calendar and takes them off again

get_gear, get_devices

gear with distance, devices with last sync and settings

garmin_sync

explicit download of a scope (all/activities/health/training/reference) and date range, with progress notifications

get_load

own load model (TSS per activity from power, pace, heart rate or RPE, with the thresholds valid on each date): CTL/ATL/TSB, ACWR 7:28, monotony and strain, flags with overridable thresholds, ISO weeks per sport, 3-zone intensity split; optional daily series, per-activity TSS/IF/load source/EF and running dynamics, monthly EF trend, monthly running dynamics at a reference pace

compare_activities

sessions side by side (ids), or the ones similar to an activity (similar_to: same type, duration and pace, optionally same route or easy only): pace, GAP, HR, power, EF, decoupling, TSS, dynamics, weather

get_readiness

morning GO / MODIFY / REST from HRV, resting HR, sleep hours and load, with Garmin's Training Readiness, Body Battery, stress and sleep score shown, not counted; overridable rules, every signal with value, reference and rating

get_thresholds, set_threshold

threshold history per date (LTHR per sport, LT1, HRmax, FTP, VO2max...; Garmin profile changes recorded automatically), heart rate and power zones per sport from the Garmin profile, and recording a test result, locally only

delete_activity, delete_workout, delete_weigh_in and overwriting a saved workout (create_workout with workout_id) are only available with GARMIN_ENABLE_DESTRUCTIVE=true.

Resources: garmin://profile, garmin://gear, garmin://devices, garmin://activity-types, garmin://sync-status, and the templates garmin://activity/{id} and garmin://workout/{id} with id completion. Prompts: weekly_review, plan_next_week.

Every response is { data, meta: { source: cache|live|partial|local, fetched_at, coverage?, sync_hint? } }, as JSON text and as structuredContent matching the tool's outputSchema; failures are { error: { code, message, hint } }.

Formulas, defaults and limits of the analytics tools: docs/analytics.md. Which Garmin Connect data is covered, and what is still missing: docs/coverage.md.

CLI

garmin-mcp-cli shares the core with the server and is handy for setup and checks:

garmin login [--strategy auto|browser|curl|fetch] [--email] [--token-path]
garmin import-tokens <file>          # garmin_tokens.json from python-garminconnect 0.3.x
garmin status [--json]
garmin sync [--scope ...] [--from --to] [--force] [--pause <s>]   # default: last 7 days
garmin activities [--from --to --type --limit --json]
garmin health <metric> [--from --to --week --json]
garmin load [--from --to] [--source auto|hrtss|garmin_load] [--flags <file.json>] [--series] [--activities] [--efficiency] [--by-sport] [--json]
garmin readiness [date] [--rules <file.json>] [--json]          # GO / MODIFY / REST for the morning
garmin thresholds [--date --param --history --json]             # LTHR, LT1, HRmax ... in effect, per sport
garmin thresholds add <date> <param> <value> [--source test|manual] [--note]
garmin thresholds export [--out <file.csv>]                     # date,param,value,source,note
garmin thresholds import <file.csv>
garmin import-activities <file.csv...>                          # Garmin Connect "Activities" CSV exports
garmin doctor                        # TLS strategy, hosts, permissions, tokens, SQLite driver
garmin serve [--transport stdio|streamable-http] [--port]
garmin logout

load, readiness and thresholds print the same results as the get_load, get_readiness and get_thresholds tools: markdown tables by default, the tool's { data, meta } envelope with --json. They read the local database only and never download; missing days come back as a note with the garmin sync command that fills them. import-activities adds activities from Garmin Connect CSV exports (English or Polish headers) for dates the synced activities do not cover, and thresholds export/import keep a copy of the threshold history in a CSV file.

Run it with npx -y garmin-mcp-cli <command> or install it globally (npm i -g garmin-mcp-cli).

Signing in

garmin login opens Garmin's real sign-in page in your installed Chrome, Edge, Brave or Chromium (a temporary profile, removed afterwards). You sign in there, including MFA or a CAPTCHA if Garmin asks; the tool only catches the one-time ticket Garmin redirects to afterwards and exchanges it for tokens. Cloudflare sees a real browser. Set GARMIN_BROWSER_PATH if your browser is not found.

Without a browser (headless server, Docker) or with --strategy curl|fetch, it asks for e-mail, password and MFA in the terminal and talks to Garmin's mobile login API, trying curl-impersonate (optional cuimp package, downloads its binary on first use) and then plain fetch. If that is blocked too, log in with Python and import the tokens; garmin doctor prints the exact command:

uvx --with "garminconnect>=0.3" python <path>/python-login.py ~/.garmin-mcp/garmin_tokens.json
garmin import-tokens ~/.garmin-mcp/garmin_tokens.json

Tokens and the database are 0600 inside a 0700 directory; the server refuses to start on looser permissions.

Remote and Docker

Streamable HTTP: GARMIN_MCP_TRANSPORT=streamable-http GARMIN_MCP_HTTP_TOKEN=<secret> npx -y garmin-mcp-server serves POST /mcp with Authorization: Bearer <secret>. Without a token it only binds to 127.0.0.1. Requests whose Host or Origin is not localhost, 127.0.0.1 or [::1] get 403 (DNS rebinding protection); behind a public hostname add it with GARMIN_HTTP_ALLOWED_HOSTS=mcp.example.com.

The server speaks MCP 2026-07-28 (server/discover, list results cached for an hour) and the 2025 revisions through the usual initialize handshake, on stdio and on HTTP, so clients on older MCP SDKs connect unchanged.

Docker: docker build -t garmin-mcp . && docker run -i -v garmin-data:/data garmin-mcp (log in with docker run -it -v garmin-data:/data garmin-mcp login).

Configuration

Precedence: CLI flag > environment > <data dir>/config.json > default. ~, $HOME and ${HOME} are always expanded.

Variable

Default

GARMIN_DATA_DIR

~/.garmin-mcp

tokens, database, config.json

GARMIN_TOKENS_FILE

$GARMIN_DATA_DIR/tokens.json

GARMIN_EMAIL, GARMIN_PASSWORD

first login only

GARMIN_REGION

global

cn switches all three hosts

GARMIN_SSO_STRATEGY

auto

auto (browser if installed, else terminal), browser, curl, fetch, import

GARMIN_BROWSER_PATH

detected

Chrome/Edge/Brave/Chromium used for the sign-in window

GARMIN_ENABLED_TOOLS, GARMIN_DISABLED_TOOLS

comma-separated allow/deny lists

GARMIN_ENABLE_DESTRUCTIVE

false

delete tools and workout overwrite

GARMIN_AUTO_FETCH

true

read tools download missing data themselves; false: only explicit syncs

GARMIN_REDACT

true

get_activity full leaves out name, profile/photo URLs, device and sensor serials and GPS; false: raw as sent

GARMIN_FIT_DOWNLOAD_DIR

$GARMIN_DATA_DIR/downloads

GARMIN_MCP_TRANSPORT, GARMIN_MCP_PORT, GARMIN_MCP_HOST, GARMIN_MCP_HTTP_TOKEN

stdio, 8000, 127.0.0.1,

GARMIN_HTTP_ALLOWED_HOSTS

comma-separated hostnames (no port, IPv6 in brackets) accepted in Host/Origin on top of localhost, 127.0.0.1, [::1]; others get 403

GARMIN_LOG_LEVEL

info

pino JSON on stderr

GARMIN_TIMEZONE

system

IANA zone for "today"

GARMIN_CONCURRENCY

4

parallel connectapi requests

GARMIN_MIN_REQUEST_INTERVAL_MS

250

spacing between request starts (±25 % jitter)

GARMIN_SYNC_CHUNK_DAYS / GARMIN_SYNC_PAUSE_S / GARMIN_SYNC_MAX_REQUESTS_PER_DAY

7 / 1-11 / 600

pacing of syncs; the pause is seconds, a random range or a fixed number

GARMIN_DI_CLIENT_IDS, GARMIN_APP_VERSION, GARMIN_APP_USER_AGENT

built in

for when Garmin changes the mobile app identity

More

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    This server cannot be deployed

    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • garmin-mcp

      yashhooda1
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI assistants to read Garmin activities and create/schedule structured workouts and multi-week training plans on Garmin Connect, syncing to the user's watch.
      1
      MIT

    • garmin-mcp

      yashhooda1
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to read Garmin activities and create/schedule structured workouts and multi-week training plans directly on Garmin Connect, syncing to your watch with guided prompts.
      1
      MIT

    • wearable-mcp

      enzojunq
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables an AI agent to read Garmin sleep, readiness and activity data, build an athlete profile, check proposed sessions against code-enforced limits and real calendar availability, and then push approved structured workouts to a Garmin watch. Plans are proposed and stored under a plan ID, so only explicitly approved sessions are ever written.
      MIT