TrainingPeaks MCP server for Claude Desktop, Code and Cowork. No API approval needed - works with any account. Query workouts, CTL/ATL/TSB fitness data, power PRs via natural language.
# Add to your Claude Code skills
git clone https://github.com/JamsusMaximus/trainingpeaks-mcpGuides for using mcp servers skills like trainingpeaks-mcp.
Last scanned: 7/4/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-07-04T06:48:04.489Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}trainingpeaks-mcp is an open-source mcp servers skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by JamsusMaximus. TrainingPeaks MCP server for Claude Desktop, Code and Cowork. No API approval needed - works with any account. Query workouts, CTL/ATL/TSB fitness data, power PRs via natural language. It has 100 GitHub stars.
Yes. trainingpeaks-mcp passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/JamsusMaximus/trainingpeaks-mcp" and add it to your Claude Code skills directory (see the Installation section above).
trainingpeaks-mcp is primarily written in Python. It is open-source under JamsusMaximus on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other MCP Servers skills you can browse and compare side by side. Open the MCP Servers category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh trainingpeaks-mcp against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
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.

Ask your AI assistant things like:
| Tool | Description |
|---|---|
tp_get_workouts |
List workouts in a date range (max 90 days) |
tp_get_workout |
Get full details for a single workout |
tp_create_workout |
Create a workout with optional interval structure, auto-computed IF/TSS, and optional planned start time |
tp_update_workout |
Update any field of an existing workout, including structured intervals and planned start time |
tp_delete_workout |
Delete a workout |
tp_copy_workout |
Copy a workout to a new date (preserves structure and planned fields) |
tp_reorder_workouts |
Reorder workouts on a given day |
tp_pair_workout |
Pair a completed workout with a planned workout (merges into one) |
tp_unpair_workout |
Unpair a workout (splits into separate completed and planned workouts) |
tp_validate_structure |
Validate interval structure without creating a workout |
tp_get_workout_comments |
Get comments on a workout |
tp_add_workout_comment |
Add a comment to a workout |
tp_get_workout_note |
Get the private workout note for a workout |
tp_set_workout_note |
Set or update the private workout note |
tp_upload_workout_file |
Upload a FIT/TCX/GPX file to a workout |
tp_download_workout_file |
Download a workout's device file |
tp_delete_workout_file |
Delete an attached file from a workout |
| Tool | Description |
|---|---|
tp_analyze_workout |
Detailed analysis with time-series data, zones, and laps |
tp_get_peaks |
Power PRs (5s-90min) and running PRs (400m-marathon) |
tp_get_workout_prs |
PRs set during a specific session |
tp_get_fitness |
CTL, ATL, and TSB trend (fitness, fatigue, form) |
tp_get_weekly_summary |
Combined workouts + fitness for a week with totals |
tp_get_atp |
Annual Training Plan - weekly TSS targets, periods, races |
| Tool | Description |
|---|---|
tp_get_athlete_settings |
Get FTP, thresholds, zones, profile |
tp_update_ftp |
Update FTP and recalculate the default power zones |
tp_update_hr_zones |
Update heart rate zones |
tp_update_speed_zones |
Update run/swim pace zones |
tp_update_nutrition |
Update daily planned calories |
tp_get_pool_length_settings |
Get pool length options |
| Tool | Description |
|---|---|
tp_log_metrics |
Log weight, HRV, sleep, steps, SpO2, pulse, RMR, injury |
tp_get_metrics |
Get health metrics for a date range |
tp_get_nutrition |
Get nutrition data for a date range |
| Tool | Description |
|---|---|
tp_get_equipment |
List bikes and shoes with distances |
tp_create_equipment |
Add a bike or shoe |
tp_update_equipment |
Update equipment details, retire |
tp_delete_equipment |
Delete equipment |
| Tool | Description |
|---|---|
tp_get_focus_event |
Get A-priority focus event with goals |
tp_get_next_event |
Get nearest future event |
tp_get_events |
List events in a date range |
tp_create_event |
Add a race/event with priority (A/B/C) and CTL target |
tp_update_event |
Update event details, attach workouts as legs (multisport) |
tp_delete_event |
Delete an event |
tp_create_note |
Create a calendar note |
tp_get_note |
Get a calendar note by ID |
tp_update_note |
Update title, description, date or visibility of a note |
tp_delete_note |
Delete a calendar note |
tp_get_note_comments |
List all comments on a note |
tp_add_note_comment |
Add a comment to a note |
tp_get_availability |
List unavailable/limited periods |
tp_create_availability |
Mark dates as unavailable or limited |
tp_delete_availability |
Remove availability entry |
| Tool | Description |
|---|---|
tp_get_libraries |
List workout library folders |
tp_get_library_items |
List templates in a library |
tp_get_library_item |
Get full template details including structure |
tp_create_library |
Create a library folder |
tp_delete_library |
Delete a library folder |
tp_create_library_item |
Save a workout template |
tp_update_library_item |
Edit a template |
tp_schedule_library_workout |
Schedule a template to a calendar date |
| Tool | Description |
|---|---|
tp_get_workout_types |
List all sport types and subtypes with IDs |
tp_get_profile |
Get athlete profile |
tp_auth_status |
Check authentication status |
tp_list_athletes |
List athletes (coach accounts) |
tp_refresh_auth |
Re-authenticate from browser cookie |
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.
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 .
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, auto
macOS 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
F12) -> Application tab -> CookiesProduction_tpAuth and copy its valuetp-mcp auth and paste when promptedOther auth commands:
tp-mcp auth-status # Check if authenticated
tp-mcp auth-clear # Remove stored cookie
Run this to get your config snippet:
tp-mcp config
Edit ~/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!
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