GARMIN_EMAIL — The email address for your Connect account. Stored only in your local .env; `npx trainbud setup` writes it for you.
GARMIN_PASSWORD — Your Connect password. Stored only in your local .env. Accounts with MFA enabled are not supported, because the unofficial library this drives cannot complete that flow.
ANTHROPIC_API_KEY — Optional, and only for the watch app's Ask card and daily insight. The MCP tools themselves need no model key: every finding is computed in code, and the model only phrases it.
Claude Code has no install link for a local command. Copy the command below and run it in a terminal.
TrainBud is an open-source MCP server that connects your Garmin Connect fitness data to Claude, Cursor, and other AI assistants. Ask about workouts, sleep, heart rate, recovery, and body composition in plain English — privately, on your machine.
Disclaimer: TrainBud is an unofficial community project. It is not affiliated with, endorsed by, or sponsored by Garmin Ltd. Garmin Connect is a trademark of Garmin Ltd.
Talk to your own fitness data. Findings computed in code against your own 28-day baselines.
0.9.0
API key
GARMIN_EMAIL, GARMIN_PASSWORD, ANTHROPIC_API_KEY
Last checked
2026-11-09
Stars
—
Tools
—
Uptime
—
Try it
Once connected to your MCP client, ask things like:
Private — credentials stay in your local .env; data is cached on your machine
Local-first — SQLite cache, session tokens in .trainbud/
Works everywhere — Windows, macOS, Linux (Node.js 22.12+)
Any MCP client — Claude Desktop, Cursor, and other stdio-compatible clients
Smart fetching — batched API calls and automatic re-auth when sessions expire
Quick start
npx trainbud setup
The setup wizard walks you through credentials, authentication, and connecting Cursor or
Claude Desktop — no MCP config editing required. Then restart your MCP client and ask it
what you did today.
To keep trainbud on your PATH instead of typing npx every time:
git clone https://github.com/Zsadigzade/trainbud.git
cd trainbud
npm install
npm run build
npm link # puts `trainbud` on your PATH; undo with `npm unlink -g trainbud`
trainbud setup
Without npm link, every trainbud <command> in this README is
node dist/index.js <command> run from the repo root. If dist/ does not exist yet,
run npm run build first.
This repo also ships project skills in .claude/skills/ for development without installing the plugin:
Command
What it does
/trainbud-setup
Install, authenticate, configure MCP, run live check
/trainbud
Ask about workouts, sleep, recovery, HR, stress, VO2 max
Open the repo in Claude Code (claude in this directory) — skills load automatically.
To use skills in every project without the plugin, copy them to ~/.claude/skills/.
After setup, restart your MCP client and try /trainbud with "What did I do today?"
Dashboard
trainbud serve hosts a dashboard at /dashboard. It is phone-first, because the
pairing flow is: you are standing next to the watch holding a phone when you approve a
code.
It shows what stands out today against your own baselines, this week against last week,
and resting heart rate and sleep plotted against your own 30-day median — all read from
the local history store, so it paints instantly and works even when your Connect session
has expired. A break in a line is a day with no measurement, not a zero.
It is also where you tell TrainBud who it is talking to:
Setting
What it changes
Name, units, primary sport, weekly goal
Every renderer, and what the AI is told about you
Thresholds
Where green becomes amber and amber becomes red — on the watch too
Watch cards
Which cards appear on the wrist and in what order, live on the next sync
AI model, tone, answer length
How the Ask card and the daily insight sound
Your own Ask questions
Up to five, 32 characters each. They lead the watch's Ask menu; the rest of the slots stay generated from what fired
Monthly spending cap
Optional. Refuses an Ask past the cap instead of spending past it
Privacy
Local feature counters, on by default, with a delete button
Usage. TrainBud runs on your own AI provider key, so every question and every daily
insight is charged to you. The dashboard shows the tokens and cost per call, the month to
date, and a 30-day chart. A model this build has no published price for is recorded with
its cost left unknown rather than as zero — a call priced at zero would make a cap that
can never trip.
Nothing on this page leaves your machine. There is no endpoint to send it to.
Garmin watch widget (Connect IQ)
View recovery, sleep, activity, stress, and VO2 max on your Garmin watch via a Connect IQ widget in ciq/.
Requires:trainbud serve running + HTTPS tunnel (same setup as web AI).
In Garmin Connect Mobile → Connect IQ → TrainBud settings, set:
Server URL — your tunnel URL (e.g. https://abc.trycloudflare.com)
Open the widget on your watch — it shows a pairing code. Approve it in the dashboard (/dashboard?token=YOUR_API_KEY) to complete setup. The dashboard swaps that token for a session cookie and drops it from the URL, so the address bar is safe to screenshot afterwards.
The glance shows recovery and sleep, or the top finding in a few characters ("RHR +4 bpm"),
from the last cached summary, so it renders without waiting on the network; once that is more
than two hours old it says so. Open it and tap or swipe to cycle through the cards you left
switched on in the dashboard. The watch calls GET /api/watch — a compact JSON summary, not
the full MCP protocol.
On the Today card, START (or tap) opens a finding to the rule it fired on — "Each of the
last 3 days was at least 3 bpm and 2 deviations above your 28-day median of 48 bpm" — and from
there it can be muted for three days (POST /api/mute). The Sleep card names what moved
last night against your own nights ("Deep 40m (1h24m)"). On the Forerunner 55, whose widget has
64 KB, those two are compiled out so the rest still fits.
Detector rules
Every finding fires on a rule you can see and move. The dashboard's Detector rules
section holds the bars — resting HR days/bpm/deviations, sleep-debt hours, HRV drop, the
training-load ratios, and "several signals together" (resting HR up, HRV down and sleep
stress up at once) — bounded so no setting makes every day, or no day, a finding. Every
surface shows the rule a finding fired on, with the numbers that were in force.
Voice (/voice)
Hold a button on your phone, ask a question out loud, hear the answer read back.
Open https://YOUR-HOST/voice?token=YOUR_API_KEY once; it trades the key for a cookie
and redirects to a clean URL.
Android / Chrome — speech recognition happens in the browser. Free, no key.
iPhone / Safari — records audio and transcribes it server-side via Groq
(whisper-large-v3-turbo, about $0.04 per hour of audio). Add the key on the dashboard.
Both — answers are spoken back, and Read me my day / Read today's insight
cost nothing at all: they are composed in code from data already on hand, not generated.
Not a watch feature and it cannot be one: Connect IQ exposes no microphone or speaker to
a widget. Not hands-free either — mobile browsers suspend the microphone when the tab is
backgrounded, so the phone has to be awake with the page in front of you.
That registers a scheduled task for the server and a watchdog that checks both halves every
five minutes — because a tunnel that answers is not a server that answers: a tunnel with
nothing behind it serves its own error page under a 200, so the link looks alive while the
watch reports HTTP -400. systemd, launchd and Docker Compose recipes are in the guide.
What stands out against your own 28-day baselines, with the rule each finding fired on
get_week_review
This week against last, the load forecast, sleep debt, and your next race
compare_workouts
One workout against your own earlier efforts of the same type and distance
remember_context
Record a goal, a race and its date, an injury, or a note
get_user_context
What is on record about you, on any date
log_subjective
How a session actually felt — RPE, soreness, mood
CLI
trainbud setup # Interactive first-time setup (recommended)
trainbud serve # Remote HTTP MCP for web AI (claude.ai, ChatGPT)
trainbud check # Live diagnostics against all tools
trainbud doctor # What the watch would see: public URL, AI key, history depth
trainbud backfill # Pull Garmin history into the local store (resumable)
trainbud findings # What stands out against your own baselines, and the rule each fired on
trainbud rederive # Rebuild sleep measurements (deep, REM, awakenings) from the local archive — no Garmin requests
trainbud start # Start the MCP server (stdio)
trainbud auth # Force re-authentication
trainbud cache clear # Clear cached data
trainbud devices # List paired watches
trainbud devices revoke <id> # Take one watch's access away
trainbud rotate status # Which secrets are set, and whether their two homes agree
trainbud rotate api-key # Replace TRAINBUD_API_KEY, and say what that invalidates
trainbud rotate ai-key # Replace the AI key in BOTH .env and app.db
trainbud status # Show session and cache status
trainbud --version # Print version
rotate ai-key writes both stores on purpose. The AI key lives in .envand in
app.db, the database copy is the one actually read, and hand-editing only the file
leaves a rotated key that never took effect.
Every one of these also works as npx trainbud <command> without installing anything.
Troubleshooting: trainbud: command not found
Either use npx trainbud <command>, or install it globally with
npm install -g trainbud. Running from a clone instead? Run npm link once from the
repo root, or call the built entry point directly with node dist/index.js doctor
(after npm run build).
Configuration
Variable
Default
Description
GARMIN_EMAIL
—
Garmin Connect email
GARMIN_PASSWORD
—
Garmin Connect password
TRAINBUD_SESSION_PATH
.trainbud/session.json
Session token storage
TRAINBUD_LOG_PATH
.trainbud/mcp.log
Log file path
TRAINBUD_CACHE_PATH
.trainbud/cache.db
SQLite cache database
CACHE_TTL_ACTIVITIES
1800
Activity cache TTL (seconds)
CACHE_TTL_SLEEP
7200
Sleep cache TTL (seconds)
CACHE_TTL_STATS
3600
Stats cache TTL (seconds)
TRAINBUD_API_KEY
auto-generated
Bearer token for HTTP MCP (trainbud serve)
TRAINBUD_HOST
127.0.0.1
Bind host for HTTP server
TRAINBUD_PORT
3847
Bind port for HTTP server
Security & privacy
Credentials live only in your local .env file — never sent to a third party
Session tokens in .trainbud/session.json are as sensitive as a password
Tool errors are sanitized before reaching the AI client
MFA is not supported by the underlying library — disable MFA or use an app-specific password
The server binds 127.0.0.1 by default. It is only reachable from the internet if
you point a tunnel at it, and every route except /health needs the API key
The dashboard takes the key once, on /dashboard?token=…, then trades it for an
HttpOnly session cookie and redirects to a clean URL — so the key does not sit in
your address bar, your history, or a screenshot
A paired watch holds a token scoped to that watch, minted at pairing and stored
on the server as a SHA-256 hash. trainbud devices lists them, trainbud devices revoke <id> takes one away — without logging out the dashboard, /mcp, or your
other watches. A watch paired before 0.5.2 holds the API key itself; re-pair it to
swap that for a scoped token
Every response carries Content-Security-Policy, X-Content-Type-Options,
X-Frame-Options and Referrer-Policy, including the 401s. HSTS is sent only on a
request that actually arrived over TLS, so the loopback dashboard stays reachable
What TrainBud is not
Not a hosted service. There is no TrainBud account and no TrainBud server. You run
it, on your machine, against your own Garmin credentials
Not an official Garmin integration. It drives an unofficial library against the
Connect web API. Garmin can change that API without notice, and does
Not MFA-compatible. If your Connect account has MFA on, this will not log in
Not free to ask. The AI features run on your own Anthropic key and are billed to
you. The dashboard meters every call and can refuse past a cap you set
Troubleshooting
Issue
Fix
Authentication failed
Verify .env credentials, run trainbud auth
MFA enabled on account
Disable MFA or use an app-specific password
Stale data
Run trainbud cache clear
Rate limited
Wait 60 seconds; cached responses are used when available
Watch shows "Not a TrainBud server" or error -400
Your public URL is answering with something that is not TrainBud's JSON — usually a tunnel that is down. Run trainbud doctor; it says exactly what came back
Watch shows "Watch not authorised"
The API key changed since the watch paired. Pair it again from the dashboard
Watch shows "AI not set up"
AI is bring-your-own-key. Paste an Anthropic key into the dashboard
No sleep/HR data
Ensure your Garmin device has synced to Garmin Connect
Server won't start
Check that GARMIN_EMAIL and GARMIN_PASSWORD are set in .env
Docker
A published image, built and exercised in CI on every push so it is not a
promise that quietly rots:
docker pull ghcr.io/zsadigzade/trainbud:latest
Or build it yourself from this repository:
docker build -t trainbud .
One thing matters more than the rest: mount a volume at /app/.trainbud.
That is where the SQLite history, the cached session and the log live. Without
it, every container restart throws away your downloaded history and
re-authenticates from scratch.
As an MCP server for a desktop client
The default entrypoint speaks MCP over stdio, so the client runs the container:
-i is required — without it the container has no stdin and the client sees a
server that connects and immediately goes quiet. The two -e flags with no
value pass the variables through from your own environment, so your credentials
stay out of the config file.
As an HTTP server, for the watch app or a web client
TRAINBUD_HOST=0.0.0.0 is needed inside a container: the server binds
127.0.0.1 by default, which is the right default on a laptop and unreachable
from outside a container.
Filling the history
trainbud setup is interactive and assumes a terminal, so with Docker do the
one-off backfill directly: