tri-train is a training platform for triathletes that syncs activities from Strava and Garmin and exposes them to Claude through a remote MCP server. Ask Claude how your last block went, why your run pace dropped, or whether you are fresh enough for Sunday's race, and it answers from your real data: activities with laps and grade-adjusted pace, weekly load and the performance management chart (CTL/ATL/TSB), sleep, HRV and resting heart rate, and your race calendar with predictions. Claude can also act: create and adjust planned workouts with structured intervals, push them to your Garmin watch, add races and write notes. Every change is journaled and can be undone. Read and write access are separate OAuth scopes, and the server enforces them on every call. Built and hosted in Switzerland by a triathlete; data stays on our own servers (Swiss revDSG / GDPR).
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 25 tools
Most tools target clearly distinct resources (activities, plans, races, profile, wellness, notes, undo) and the descriptions explicitly delineate boundaries, including a cross-reference from training_get to training_plan_list. The weakest spots are training_update (which only corrects activity markers despite a very generic name) versus training_plan_update, and training_plan_delete ('sagt ab') versus training_plan_update, but the long descriptions disambiguate these adequately.
Every tool carries the same training_ prefix in snake_case, and sub-resources follow a predictable list/get/create/update/delete pattern (plan_*, race_*, list_notes/get_note). Minor deviations exist: training_stats, training_profile, training_wellness, training_readiness, training_changes are noun-only queries without a get/list verb, and training_update is a bare verb rather than verb_noun.
25 tools is on the heavy side, but the domain genuinely spans activities, plan lifecycle, Garmin push, races plus prognosis, thresholds, wellness, readiness, stats and undo — each tool occupies a real niche. It is at the upper bound rather than bloated; a few read tools (readiness, wellness, profile) could not easily be merged without losing clarity.
Full lifecycle coverage: activities list/get/update, plans create/list/update/delete/push-to-Garmin, races CRUD plus prognosis, thresholds get/update, notes write/get/list, stats, load projection, readiness, wellness, search, and a journal-based undo covering all write tools. Deliberate omissions (no activity delete because Strava resyncs) are documented and routed to excluded_from_stats, so there are no dead ends.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Garmin data in Claude: 135 tools — activities, sleep, HRV, training, workouts. Free, open source.
Connect Claude to your Intervals.icu watch data for fitness, workout review, and plan writing.
Garmin data in Claude & ChatGPT via the Garmin Health API. OAuth sign-in, no password sharing.
Pace is a remote MCP server that exposes wearable and fitness data to Claude via the Model Context Protocol. It connects to Garmin, Oura, Whoop, Polar, Fitbit and 20+ devices and provides 15 tools for querying sleep, activity, recovery, and training data. Hosted on Google Cloud Run, OAuth 2.1 authentication, Streamable HTTP transport. Instructions: First you need to create an account at: https://pacetraining.co and connect your wearables. After that you can connect the remote Server via Custom Connector in Claude and OAuth 2.1 Flow startet.
Add one secure layer between your agents and this server.
