TrainingPeaks-MCP
TrainingPeaks MCP Server
Connect TrainingPeaks to Claude and other AI assistants via the Model Context Protocol (MCP). Query workouts, build structured intervals, manage your calendar, track fitness trends, and control your training through natural conversation.
No API approval required. The official Training Peaks API is approval-gated, but this server uses secure cookie authentication that any user can set up in minutes. Your cookie is stored in your system keyring, never transmitted anywhere except to TrainingPeaks.
What You Can Do

Ask your AI assistant things like:
"Build me a 4x8min threshold session for Tuesday with warm-up and cool-down"
"Schedule my mobility session for April 14, 2026 at 16:45"
"Compare my FTP progression this year vs last year"
"Copy last week's long ride to this Saturday"
"Log my weight at 74.5kg and sleep at 7.5 hours"
"What's my weekly TSS so far? Am I on track for my ATP target?"
"Show my race calendar and how many weeks until my A race"
"Set my FTP to 310 and update my power zones"
"Add a calendar note for next Monday: rest day, travel"
Related MCP server: TrainingPeaks MCP Server
Tools (58)
Workouts
Tool | Description |
| List workouts in a date range (max 90 days) |
| Get full details for a single workout |
| Create a workout with optional interval structure, auto-computed IF/TSS, and optional planned start time |
| Update any field of an existing workout, including structured intervals and planned start time |
| Delete a workout |
| Copy a workout to a new date (preserves structure and planned fields) |
| Reorder workouts on a given day |
| Pair a completed workout with a planned workout (merges into one) |
| Unpair a workout (splits into separate completed and planned workouts) |
| Validate interval structure without creating a workout |
| Get comments on a workout |
| Add a comment to a workout |
| Upload a FIT/TCX/GPX file to a workout |
| Download a workout's device file |
| Delete an attached file from a workout |
Analysis & Performance
Tool | Description |
| Detailed analysis with time-series data, zones, and laps |
| Power PRs (5s-90min) and running PRs (400m-marathon) |
| PRs set during a specific session |
| CTL, ATL, and TSB trend (fitness, fatigue, form) |
| Combined workouts + fitness for a week with totals |
| Annual Training Plan - weekly TSS targets, periods, races |
Athlete Settings
Tool | Description |
| Get FTP, thresholds, zones, profile |
| Update FTP and recalculate the default power zones |
| Update heart rate zones |
| Update run/swim pace zones |
| Update daily planned calories |
| Get pool length options |
Health Metrics
Tool | Description |
| Log weight, HRV, sleep, steps, SpO2, pulse, RMR, injury |
| Get health metrics for a date range |
| Get nutrition data for a date range |
Equipment
Tool | Description |
| List bikes and shoes with distances |
| Add a bike or shoe |
| Update equipment details, retire |
| Delete equipment |
Events & Calendar
Tool | Description |
| Get A-priority focus event with goals |
| Get nearest future event |
| List events in a date range |
| Add a race/event with priority (A/B/C) and CTL target |
| Update event details |
| Delete an event |
| Create a calendar note |
| Delete a calendar note |
| List unavailable/limited periods |
| Mark dates as unavailable or limited |
| Remove availability entry |
Workout Library
Tool | Description |
| List workout library folders |
| List templates in a library |
| Get full template details including structure |
| Create a library folder |
| Delete a library folder |
| Save a workout template |
| Edit a template |
| Schedule a template to a calendar date |
Reference & Auth
Tool | Description |
| List all sport types and subtypes with IDs |
| Get athlete profile |
| Check authentication status |
| List athletes (coach accounts) |
| Re-authenticate from browser cookie |
Setup Options
Option A: Auto-Setup with Claude Code
If you have Claude Code, paste this prompt:
Set up the TrainingPeaks MCP server from https://github.com/JamsusMaximus/trainingpeaks-mcp - clone it, create a venv, install it, then walk me through getting my TrainingPeaks cookie from my browser and run tp-mcp auth. Finally, add it to my Claude Desktop config.Claude will handle the installation and guide you through authentication step-by-step.
Option B: Manual Setup
Step 1: Install
git clone https://github.com/JamsusMaximus/trainingpeaks-mcp.git
cd trainingpeaks-mcp
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e .Step 2: Authenticate
Option A: Auto-extract from browser (easiest)
If you're logged into TrainingPeaks in your browser:
pip install tp-mcp[browser] # One-time: install browser support
tp-mcp auth --from-browser chrome # Or: firefox, safari, edge, automacOS note: You may see security prompts for Keychain or Full Disk Access. This is normal - browser cookies are encrypted and require permission to read.
Option B: Manual cookie entry
Log into app.trainingpeaks.com
Open DevTools (
F12) -> Application tab -> CookiesFind
Production_tpAuthand copy its valueRun
tp-mcp authand paste when prompted
Other auth commands:
tp-mcp auth-status # Check if authenticated
tp-mcp auth-clear # Remove stored cookieStep 3: Add to Claude Desktop
Run this to get your config snippet:
tp-mcp configEdit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) and paste it inside mcpServers. Example with multiple servers:
{
"mcpServers": {
"some-other-server": {
"command": "npx",
"args": ["some-other-mcp"]
},
"trainingpeaks": {
"command": "/Users/you/trainingpeaks-mcp/.venv/bin/tp-mcp",
"args": ["serve"]
}
}
}Restart Claude Desktop. You're ready to go!
Structured Workouts
Create workouts with full interval structure. The server auto-computes duration, IF, and TSS from the structure:
{
"date": "2026-03-01",
"sport": "Bike",
"title": "Sweet Spot Intervals",
"structure": {
"primaryIntensityMetric": "percentOfFtp",
"steps": [
{"name": "Warm Up", "duration_seconds": 600, "intensity_min": 40, "intensity_max": 55, "intensityClass": "warmUp"},
{"type": "repetition", "reps": 4, "steps": [
{"name": "Sweet Spot", "duration_seconds": 480, "intensity_min": 88, "intensity_max": 93, "intensityClass": "active"},
{"name": "Recovery", "duration_seconds": 120, "intensity_min": 50, "intensity_max": 60, "intensityClass": "rest"}
]},
{"name": "Cool Down", "duration_seconds": 600, "intensity_min": 40, "intensity_max": 55, "intensityClass": "coolDown"}
]
}
}The LLM builds this JSON naturally from conversation - just say "build me 4x8min sweet spot with 2min rest".
You can use the same simplified structure object with tp_update_workout:
{
"workout_id": "3658666303",
"duration_minutes": 57,
"tss_planned": 62.3,
"structure": {
"primaryIntensityMetric": "percentOfThresholdHr",
"steps": [
{"name": "Warm-up", "duration_seconds": 900, "intensity_min": 65, "intensity_max": 80, "intensityClass": "warmUp"},
{"type": "repetition", "name": "4x5min controlled tempo", "reps": 4, "steps": [
{"name": "Interval", "duration_seconds": 300, "intensity_min": 89, "intensity_max": 94, "intensityClass": "active"},
{"name": "Jog recovery", "duration_seconds": 180, "intensity_min": 65, "intensity_max": 83, "intensityClass": "rest"}
]},
{"name": "Cool-down", "duration_seconds": 600, "intensity_min": 65, "intensity_max": 80, "intensityClass": "coolDown"}
]
}
}If duration_minutes and tss_planned are omitted, they are derived from the structure. If you pass them explicitly, they override the derived values.
For advanced round-trip use cases, tp_create_workout and tp_update_workout also accept a native structured_workout payload in TrainingPeaks builder format. When a workout already has a native structure, tp_get_workout returns it as structured_workout.
{
"workout_id": "3658666303",
"structured_workout": {
"structure": [],
"polyline": [],
"primaryLengthMetric": "duration",
"primaryIntensityMetric": "percentOfFtp",
"primaryIntensityTargetOrRange": "range"
}
}Use either structure or structured_workout in a single create/update call, not both.
For planned workout scheduling, tp_create_workout and tp_update_workout accept:
YYYY-MM-DDfor all-day planning on a calendar dateYYYY-MM-DDTHH:MM:SSfor a planned start time on that date
TrainingPeaks stores planned workout times separately from the calendar day. Internally this means:
workoutDaystays at midnight for the selected datestartTimePlannedstores the planned start timeplanned end time is derived from
startTimePlanned + totalTimePlanned
Example with a planned start time:
{
"date": "2026-04-14T16:45:00",
"sport": "Strength",
"title": "Core & Mobility",
"duration_minutes": 60,
"description": "Core stabilisation and stretching."
}What is MCP?
Model Context Protocol is an open standard for connecting AI assistants to external data sources. MCP servers expose tools that AI models can call to fetch real-time data, enabling assistants like Claude to access your Training Peaks account through natural language.
Security
TL;DR: Your cookie is encrypted on disk, exchanged for short-lived OAuth tokens, never shown to Claude, and only ever sent to TrainingPeaks. The server has no network ports.
This server is designed with defence-in-depth. Your TrainingPeaks session cookie is sensitive - it grants access to your training data - so we treat it accordingly.
Write access: v2.0 adds full calendar management (create, update, delete workouts, events, notes, equipment, settings). All mutations go through Pydantic validation. The server cannot access billing or payment info.
Cookie Storage
Platform | Primary Storage | Fallback |
macOS | System Keychain | Encrypted file |
Windows | Windows Credential Manager | Encrypted file |
Linux | Secret Service (GNOME/KDE) | Encrypted file |
Your cookie is never stored in plaintext. The encrypted file fallback uses AES-256-GCM authenticated encryption with a PBKDF2-derived key (600,000 iterations) and a machine-specific salt.
Cookie Never Leaks to AI
The AI assistant (Claude) never sees your cookie value. Multiple layers ensure this:
Return value sanitisation: Tool results are scrubbed for any keys containing
cookie,token,auth,credential,password, orsecretbefore being sent to ClaudeMasked repr(): The
BrowserCookieResultandCredentialResultclasses override__repr__to showcookie=<present>instead of the actual valueSanitised exceptions: Error messages use only exception type names, never full messages that could contain data
No logging: Cookie values are never written to any log
Domain Hardcoding (Cannot Be Changed)
The browser cookie extraction only accesses .trainingpeaks.com:
# From src/tp_mcp/auth/browser.py - HARDCODED, not a parameter
cj = func(domain_name=".trainingpeaks.com")Claude cannot modify this via tool parameters. The only parameter is browser (chrome/firefox/etc), not the domain. To change the domain would require modifying the source code.
No Network Exposure
The MCP server uses stdio transport only - it communicates with Claude Desktop via stdin/stdout, not over the network. There is no HTTP server, no open ports, no remote access.
Open Source
This server is fully open source. You can audit every line of code before running it. Key security files:
src/tp_mcp/auth/browser.py- Cookie extraction with hardcoded domainsrc/tp_mcp/auth/encrypted.py- AES-256-GCM credential encryptionsrc/tp_mcp/tools/_validation.py- Pydantic input validationsrc/tp_mcp/tools/refresh_auth.py- Result sanitisationtests/test_tools/test_refresh_auth_security.py- Security tests
Authentication Flow
The server uses a two-step authentication process:
Cookie to OAuth Token: Your stored cookie is exchanged for a short-lived OAuth access token (expires in 1 hour)
Automatic Refresh: Tokens are cached in memory and automatically refreshed before expiry
This means:
You only need to authenticate once with
tp-mcp authAPI calls use proper Bearer token auth, not cookies
If your session cookie expires (typically after several weeks), use
tp_refresh_authin Claude or runtp-mcp authagain
Development
pip install -e ".[dev]"
pytest tests/ -v
mypy src/
ruff check src/Licence
MIT
Available Tools
85 toolstp_add_athletes_to_groupAdd athletes to groupAIdempotent
Add one or more athletes to a group. Moving an athlete = add to the new group + remove from the old one.
Inputs: group_id (required), athlete_ids (required).
tp_add_note_commentAdd note commentA
Append a comment to a calendar note's thread. Repeating the call posts a duplicate. Note ID from tp_list_notes or tp_create_note.
Inputs: comment (required), note_id (required), athlete.
tp_add_workout_commentAdd workout commentA
Append a comment to a workout's thread - visible to both athlete and coach. Repeating the call posts a duplicate. For a private note use tp_set_workout_note instead.
Inputs: comment (required), workout_id (required), athlete.
tp_analyze_workoutAnalyze workoutARead-onlyIdempotent
Get workout analysis: metrics, zones, laps. Saves full time-series to JSON file.
Inputs: workout_id (required), athlete.
tp_apply_training_planApply training planA
Apply a training plan to an athlete's calendar from a start date by copying each plan workout (with structure) to start_date + its relative day. Targets the athlete given via the athlete parameter.
Inputs: plan_id (required), start_date (required), athlete.
tp_auth_statusCheck auth statusARead-onlyIdempotent
Check auth status. Use only when other tools return auth errors.
Inputs: no named parameters.
tp_copy_workoutCopy workoutA
Copy a workout to a new date. Copies structure, description, planned fields.
Inputs: workout_id (required), target_date (required), title, athlete.
tp_create_availabilityCreate availabilityA
Mark a date range as unavailable for training (or limited to certain sports). limited=false means fully unavailable; with limited=true, sport_types lists the sports that REMAIN available. Returns availability_id, needed for tp_delete_availability.
Inputs: end_date (required), start_date (required), athlete, limited, +2 more.
tp_create_equipmentCreate equipmentA
Add a bike or shoes to the athlete's equipment list. type is 'bike' or 'shoe'; bike-only fields are rejected on shoes. The API returns no ID on create - verify with tp_get_equipment afterwards.
Inputs: name (required), type (required), brand, model, +8 more.
tp_create_eventCreate eventB
Create a race/event with priority (A/B/C) and CTL target.
Inputs: date (required), name (required), athlete, priority, +4 more.
tp_create_groupCreate groupB
Create a new athlete group.
Inputs: name (required).
tp_create_libraryCreate libraryA
Create an empty workout library (a folder for reusable templates). Returns library_id; add templates with tp_create_library_item.
Inputs: name (required), athlete.
tp_create_library_itemCreate library itemC
Save a workout template to a library.
Inputs: name (required), library_id (required), sport_type_id (required), sport_family_id (required), +5 more.
tp_create_noteCreate noteC
Create a calendar note.
Inputs: date (required), title (required), athlete, description.
tp_create_strength_workoutCreate strength workoutA
Create a structured strength/gym workout on the athlete's calendar. Blocks of exercises (from tp_search_exercises) with sets and parameters (Reps, WeightKg, Duration, …).
Inputs: date (required), title (required), blocks (required), athlete, +1 more.
tp_create_workoutCreate workoutA
Create a planned workout with optional simplified interval structure or native TrainingPeaks structured_workout payload. Duration is auto-computed only from simplified structure when not provided.
Inputs: date (required), sport (required), title (required), rpe, +11 more.
tp_create_zonesCreate zonesA
Create a NEW per-sport zone set for an athlete that has none for that sport (use tp_update_ftp/hr_zones/speed_zones to change an EXISTING set). Bands are computed by TrainingPeaks' calculator for the chosen method (see tp_get_zone_methods). Returns ZONES_EXIST if the set is already present, or TEST_BASED_METHOD for test-derived methods (Distance/Time) — those are set up via a test in the TP UI.
Inputs: metric (required), workout_type (required), calculation_method (required), pace, +5 more.
tp_delete_availabilityDelete availabilityADestructiveIdempotent
Remove an availability entry so those dates become plannable again. availability_id from tp_get_availability or the create response.
Inputs: availability_id (required), athlete.
tp_delete_equipmentDelete equipmentCDestructiveIdempotent
Delete equipment.
Inputs: equipment_id (required), athlete.
tp_delete_eventDelete eventADestructiveIdempotent
Permanently delete a race/event from the calendar - irreversible. Event ID from tp_get_events. Calendar workouts are separate: delete those with tp_delete_workout.
Inputs: event_id (required), athlete.
tp_delete_groupDelete groupADestructiveIdempotent
Delete an athlete group (the grouping only — athletes are not deleted). The default group cannot be deleted.
Inputs: group_id (required).
tp_delete_libraryDelete libraryADestructiveIdempotent
Permanently delete a library AND every template inside it - irreversible, and there is no per- template delete. Schedule anything you want to keep first.
Inputs: library_id (required), athlete.
tp_delete_noteDelete noteADestructiveIdempotent
Permanently delete a calendar note and its comment thread - irreversible. Note ID from tp_list_notes.
Inputs: note_id (required), athlete.
tp_delete_strength_workoutDelete strength workoutADestructiveIdempotent
Delete a strength workout by ID.
Inputs: workout_id (required), athlete.
tp_delete_workoutDelete workoutADestructiveIdempotent
Permanently delete a workout from the calendar - irreversible, applies to planned and completed workouts alike. Workout ID from tp_get_workouts.
Inputs: workout_id (required), athlete.
tp_delete_workout_fileDelete workout fileADestructiveIdempotent
Delete a workout file by file_id. Get file_id from tp_get_workout device_files/attachment_files.
Inputs: file_id (required), workout_id (required), athlete.
tp_download_workout_fileDownload workout fileARead-onlyIdempotent
Download a workout file by file_id. Get file_id from tp_get_workout device_files/attachment_files.
Inputs: file_id (required), workout_id (required), athlete, output_path.
tp_get_athlete_settingsGet athlete settingsARead-onlyIdempotent
Get athlete account settings and profile fields (athlete type, linked coach, preferences, units). To change training values use tp_update_ftp / tp_update_hr_zones / tp_update_speed_zones.
Inputs: athlete.
tp_get_atpGet ATP (annual training plan)ARead-onlyIdempotent
Get Annual Training Plan - weekly TSS targets, training periods, races. Max 90 days.
Inputs: end_date (required), start_date (required), athlete.
tp_get_availabilityGet availabilityARead-onlyIdempotent
Get availability entries for a date range.
Inputs: end_date (required), start_date (required), athlete.
tp_get_equipmentGet equipmentARead-onlyIdempotent
List equipment (bikes, shoes).
Inputs: type, athlete.
tp_get_eventsGet eventsARead-onlyIdempotent
List events in a date range.
Inputs: end_date (required), start_date (required), athlete.
tp_get_fitnessGet fitnessARead-onlyIdempotent
Get fitness/fatigue trend (CTL/ATL/TSB). Supports historical date ranges.
Inputs: days, athlete, end_date, start_date.
tp_get_focus_eventGet focus eventBRead-onlyIdempotent
Get the A-priority focus event with goals and results.
Inputs: athlete.
tp_get_librariesGet librariesARead-onlyIdempotent
List workout library folders.
Inputs: athlete.
tp_get_library_itemGet library itemARead-onlyIdempotent
Get one workout template in full, including its interval structure - use before tp_schedule_library_workout or when reusing structure. IDs from tp_get_library_items.
Inputs: item_id (required), library_id (required), athlete.
tp_get_library_itemsGet library itemsARead-onlyIdempotent
List the workout templates in one library (slim listing). library_id from tp_get_libraries. For a template's full interval structure use tp_get_library_item.
Inputs: library_id (required), athlete.
tp_get_metricsGet metricsARead-onlyIdempotent
Get health metrics for a date range.
Inputs: end_date (required), start_date (required), athlete.
tp_get_next_eventGet next eventARead-onlyIdempotent
Get the nearest future planned event.
Inputs: athlete.
tp_get_noteGet noteARead-onlyIdempotent
Get a calendar note by ID.
Inputs: note_id (required), athlete.
tp_get_note_commentsGet note commentsARead-onlyIdempotent
Get all comments on a calendar note.
Inputs: note_id (required), athlete.
tp_get_nutritionGet nutritionCRead-onlyIdempotent
Get nutrition data for a date range.
Inputs: end_date (required), start_date (required), athlete.
tp_get_peaksGet peaksARead-onlyIdempotent
Get an athlete's top performances for one sport and PR type over a period (days, default 90). Bike pr_type: power1min/5min/20min; Run: speed5K/10K/Half. For PRs from a single workout use tp_get_workout_prs.
Inputs: sport (required), pr_type (required), days, athlete.
tp_get_pool_length_settingsGet pool length settingsBRead-onlyIdempotent
Get pool length settings.
Inputs: athlete.
tp_get_profileGet profileARead-onlyIdempotent
Get athlete profile. Rarely needed - other tools work without it.
Inputs: athlete.
tp_get_strength_summaryGet strength summaryARead-onlyIdempotent
Get a strength workout's compliance summary (blocks/prescriptions/sets completed).
Inputs: workout_id (required), athlete.
tp_get_strength_workoutGet strength workoutARead-onlyIdempotent
Get a strength workout's full detail by ID: blocks, exercises, and sets with prescribed vs executed values (Reps, WeightKg, …), plus RPE, feel and compliance. Get IDs from tp_get_strength_workouts.
Inputs: workout_id (required), athlete.
tp_get_strength_workoutsGet strength workoutsARead-onlyIdempotent
List structured strength/gym workouts in a date range. Strength workouts live on a separate API and do NOT appear in tp_get_workouts; use this to find them and their IDs, then tp_get_strength_workout for full detail. Returns date, title, duration, compliance, set totals, and an exercise preview.
Inputs: end_date (required), start_date (required), athlete.
tp_get_training_planGet training planARead-onlyIdempotent
Summary of one training plan: weeks, per-week duration/distance, sport breakdown, description.
Inputs: plan_id (required), athlete.
tp_get_training_plan_workoutsGet training plan workoutsARead-onlyIdempotent
All workouts of a training plan laid out by week/day (sport, title, description, duration, TSS, has_structure).
Inputs: plan_id (required), athlete.
tp_get_weekly_summaryGet weekly summaryARead-onlyIdempotent
Combined view of workouts + fitness for a week. Totals TSS, duration, end-of-week CTL/ATL/TSB.
Inputs: athlete, week_of.
tp_get_workoutGet workoutARead-onlyIdempotent
Get workout details by ID. Use after tp_get_workouts.
Inputs: workout_id (required), athlete.
tp_get_workout_commentsGet workout commentsARead-onlyIdempotent
List the comment thread on a workout (athlete and coach comments with author and timestamp). Workout ID from tp_get_workouts. For the private workout note use tp_get_workout_note.
Inputs: workout_id (required), athlete.
tp_get_workout_noteGet workout noteARead-onlyIdempotent
Get the private workout note for a workout.
Inputs: workout_id (required), athlete.
tp_get_workout_prsGet workout PRsARead-onlyIdempotent
List personal records set during one completed workout. Returns an empty list when none. For an athlete's bests across a period use tp_get_peaks.
Inputs: workout_id (required), athlete.
tp_get_workoutsGet workoutsARead-onlyIdempotent
List workouts in date range. Query only days needed. Max 90 days. Does NOT include strength-builder gym workouts — use tp_get_strength_workouts for those.
Inputs: end_date (required), start_date (required), type, athlete.
tp_get_workout_typesGet workout typesARead-onlyIdempotent
List all sport types and subtypes with IDs. Use to find subtype_id for create/update.
Inputs: no named parameters.
tp_get_zone_methodsGet zone methodsARead-onlyIdempotent
List available zone-calculation methods per metric (power / heartrate / speed), each with its zone count and zone labels. TP has no method-names endpoint and settings store only an opaque method int; this probes the zone calculator (read-only) to fingerprint each method by its zone labels. derives_threshold marks methods that derive the threshold from a (field-)test, so a direct threshold can't be set. Coach-scoped (uses your own user), not athlete-specific.
Inputs: metric.
tp_list_athletesList athletesARead-onlyIdempotent
List athletes available to this account (coach accounts).
Inputs: no named parameters.
tp_list_athletes_in_groupList athletes in groupARead-onlyIdempotent
List the athletes in one athlete group, with names resolved from the coach's roster. Use tp_list_groups to get group_id.
Inputs: group_id (required).
tp_list_groupsList groupsARead-onlyIdempotent
List the coach's athlete groups (TP exposes these as tags). Returns id, name, athlete_count, is_default.
Inputs: no named parameters.
tp_list_notesList notesARead-onlyIdempotent
List calendar notes for a date range.
Inputs: end_date (required), start_date (required), athlete.
tp_list_training_plansList training plansARead-onlyIdempotent
List the coach's authored multi-week training plans (id, title, weeks, workout count, total hours, category, price).
Inputs: athlete.
tp_log_metricsLog metricsB
Log health metrics (weight, HRV, sleep, steps, etc.) for a date.
Inputs: date (required), hrv, rmr, spo2, +6 more.
tp_pair_workoutPair workoutAIdempotent
Pair a completed workout with a planned workout. Attaches the completed data to the planned workout, merging them into one.
Inputs: planned_workout_id (required), completed_workout_id (required), athlete.
tp_refresh_authRefresh authAIdempotent
Refresh auth by extracting cookie from user's browser. Use when other tools return auth errors.
Inputs: browser.
tp_remove_athletes_from_groupRemove athletes from groupADestructiveIdempotent
Remove one or more athletes from a group.
Inputs: group_id (required), athlete_ids (required).
tp_rename_groupRename groupAIdempotent
Rename an athlete group. The default group cannot be renamed.
Inputs: name (required), group_id (required).
tp_reorder_workoutsReorder workoutsAIdempotent
Reorder the workouts displayed on a single day. Pass every workout ID for that day (from tp_get_workouts) in the desired order. Changes display order only - dates and content untouched.
Inputs: workout_ids (required), athlete.
tp_schedule_library_workoutSchedule library workoutA
Schedule a library template to a calendar date, for yourself or (coach accounts) for one or many athletes.
Inputs: date (required), item_id (required), library_id (required), athlete, +1 more.
tp_search_exercisesSearch exercisesARead-onlyIdempotent
Search the built-in strength exercise library by name (offline). Returns library exercise IDs to use in tp_create_strength_workout, plus each exercise's native parameters and a demo video URL.
Inputs: query (required), limit, muscle_group.
tp_set_workout_noteSet workout noteAIdempotent
Set or update the private workout note for a workout.
Inputs: note (required), workout_id (required), athlete.
tp_unpair_workoutUnpair workoutAIdempotent
Unpair a workout. Detaches the completed workout file from the planned workout, creating two separate workouts. No data is lost.
Inputs: workout_id (required), athlete.
tp_update_equipmentUpdate equipmentCIdempotent
Update equipment details.
Inputs: equipment_id (required), name, brand, model, +7 more.
tp_update_eventUpdate eventAIdempotent
Update fields on an existing race/event (name, date, priority, distance, description, attached workout legs). Only the provided fields change. Event ID from tp_get_events; events more than ~2 years from today cannot be resolved for update.
Inputs: event_id (required), date, name, athlete, +6 more.
tp_update_ftpUpdate FTPAIdempotent
Update FTP (power threshold) and rescale the matching power-zone set, preserving its calculation method.
Inputs: ftp (required), athlete, workout_type.
tp_update_hr_zonesUpdate HR zonesCIdempotent
Update heart rate zones.
Inputs: max_hr, athlete, resting_hr, threshold_hr, +1 more.
tp_update_library_itemUpdate library itemCIdempotent
Edit a workout template.
Inputs: item_id (required), library_id (required), tss, name, +6 more.
tp_update_noteUpdate noteAIdempotent
Update a calendar note. Provide at least one of: title, description, date, is_hidden.
Inputs: note_id (required), date, title, athlete, +2 more.
tp_update_nutritionUpdate nutritionAIdempotent
Update daily planned calories.
Inputs: planned_calories (required), athlete.
tp_update_speed_zonesUpdate speed zonesCIdempotent
Update run/swim pace zones.
Inputs: athlete, run_threshold_pace, swim_threshold_pace.
tp_update_strength_workoutUpdate strength workoutAIdempotent
Update an existing strength workout in place: replace or append blocks, retitle, or mark it complete. Preserves everything else, including Garmin-derived TSS and the attached FIT file — so this is the correct way to fill in a device-synced workout that arrived with no structure. Never delete-and-recreate for that: exercise detail is rebuildable, HR-derived training load is not.
Inputs: workout_id (required), mode, title, blocks, +4 more.
tp_update_workoutUpdate workoutAIdempotent
Update fields of an existing workout. Supports the same simplified interval structure format as tp_create_workout plus an optional native structured_workout payload, then fetches existing, merges, and saves.
Inputs: workout_id (required), rpe, date, tags, +14 more.
tp_upload_workout_fileUpload workout fileA
Upload a workout file (.fit, .tcx, .gpx) to an existing workout.
Inputs: workout_id (required), athlete, file_path, workout_day, +1 more.
tp_validate_structureValidate structureARead-onlyIdempotent
Validate workout interval structure without creating a workout. Returns block count, duration, estimated IF/TSS.
Inputs: structure (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 85 tools
Most tools target a distinct resource and action, and descriptions clearly separate overlapping concepts like workout notes vs. comments and cardio vs. strength workouts. A few pairs (tp_get_workout vs. tp_get_strength_workout, tp_get_workout_note vs. tp_get_note_comments) require careful reading, but no tools appear to do exactly the same thing.
The vast majority follow a consistent tp_verb_noun snake_case pattern (e.g., tp_get_workouts, tp_update_ftp, tp_delete_equipment). Minor exceptions like tp_auth_status and tp_log_metrics break the pattern slightly, but the overall convention is highly predictable.
85 tools is far beyond the typical well-scoped MCP server and even for a broad platform this creates a significant navigation burden. While each tool may have a legitimate purpose, the sheer number makes it difficult for an agent to efficiently discover and select the right tool.
The tool surface is extremely comprehensive, covering workouts, strength training, events, notes, equipment, libraries, groups, metrics, and more. Minor gaps exist, such as no training plan creation/editing and no per-template library deletion, but these are workable and do not create dead ends for most coaching workflows.
Maintenance
Related MCP Connectors
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).
Connect Intervals.icu to Claude and ChatGPT: read training, plan workouts. Training never stored.
Connect Claude to your Intervals.icu watch data for fitness, workout review, and plan writing.
Garmin data in Claude: 135 tools — activities, sleep, HRV, training, workouts. Free, open source.
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server for Intervals.icu integration. Access your training data, wellness metrics, and performance analysis through Claude and other LLMs.4839MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server for TrainingPeaks with an analytics focus — enabling real-time querying of training data, performance trends, CTL/ATL/TSB analysis, and training load optimization through Claude Desktop.1416 PyPIMIT
- AlicenseAqualityCmaintenanceLocal MCP server that connects Claude Desktop with Garmin and Apple Health data to read training and recovery, estimate heart rate and pace zones, analyze performance, and create structured workouts.22MIT
- FlicenseNot gradedqualityCmaintenanceMCP server for TrainingPeaks that reads workouts, fitness metrics (CTL/ATL/TSB), and health data, and creates/updates/deletes planned workouts. Enables AI-powered training plan management and automated adjustment based on performance, fatigue, and injury.-