// SCAN REPORT

TrainingPeaks-MCP

65 tools. 33 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated: 27 Jun 2026

33 can modify or destroy data

32 read-only

65 tools total

Community server · catalogue entry verified 27/06/2026

How to control TrainingPeaks-MCP ↓

TOOL MAP

What TrainingPeaks-MCP exposes to your agents

Read (32) Write / Execute (26) Destructive / Financial (7)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous TrainingPeaks-MCP tools

Destructive · High tp_delete_availability This tool permanently removes availability entries without the ability to undo the action. Destructive · High tp_delete_equipment This tool irreversibly removes equipment records from the TrainingPeaks system. Destructive · High tp_delete_event The tool performs an irreversible deletion of an event object. Destructive · High tp_delete_library This tool permanently removes a library folder and all associated templates without reversibility.

33 of TrainingPeaks-MCP's 65 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control TrainingPeaks-MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and TrainingPeaks-MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "tp_delete_availability": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "tp_add_note_comment": {
    "limits": [
      {
        "counter": "tp_add_note_comment_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "tp_analyze_workout": {
    "limits": [
      {
        "counter": "tp_analyze_workout_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register TrainingPeaks-MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON TRAININGPEAKS-MCP →

Instant setup, no code required.

FULL CATALOGUE

All 65 TrainingPeaks-MCP tools

DESTRUCTIVE 7 tools

Destructive tp_delete_availability Remove an availability entry. Destructive tp_delete_equipment Delete equipment. Destructive tp_delete_event Delete an event. Destructive tp_delete_library Delete a library folder and all templates. Destructive tp_delete_note Delete a calendar note. Destructive tp_delete_workout Delete a workout. Destructive tp_delete_workout_file Delete a workout file by file_id. Get file_id from tp_get_workout device_files/attachment_files.

WRITE 26 tools

Write tp_add_note_comment Add a comment to a calendar note. Write tp_add_workout_comment Add a comment to a workout. Write tp_copy_workout Copy a workout to a new date. Copies structure, description, planned fields. Write tp_create_availability Mark dates as unavailable or limited. Write tp_create_equipment Add new equipment (bike or shoe). Write tp_create_event Create a race/event with priority (A/B/C) and CTL target. Write tp_create_library Create a workout library folder. Write tp_create_library_item Save a workout template to a library. Write tp_create_note Create a calendar note. Write tp_create_workout Create a planned workout with optional simplified interval structure Write tp_log_metrics Log health metrics (weight, HRV, sleep, steps, etc.) for a date. Write tp_pair_workout Pair a completed workout with a planned workout. Attaches the Write tp_reorder_workouts Reorder workouts on a given day. Write tp_schedule_library_workout Schedule a library template to a calendar date. Write tp_set_workout_note Set or update the private workout note for a workout. Write tp_unpair_workout Unpair a workout. Detaches the completed workout file from the Write tp_update_equipment Update equipment details. Write tp_update_event Update an event. Write tp_update_ftp Update FTP and recalculate the default power zones. Write tp_update_hr_zones Update heart rate zones. Write tp_update_library_item Edit a workout template. Write tp_update_note Update a calendar note. Provide at least one of: title, description, date, is_hidden. Write tp_update_nutrition Update daily planned calories. Write tp_update_speed_zones Update run/swim pace zones. Write tp_update_workout Update fields of an existing workout. Supports the same simplified Write tp_upload_workout_file Upload a workout file (.fit, .tcx, .gpx) to an existing workout.

READ 32 tools

Read tp_analyze_workout Get workout analysis: metrics, zones, laps. Saves full time-series to JSON file. Read tp_auth_status Check auth status. Use only when other tools return auth errors. Read tp_download_workout_file Download a workout file by file_id. Read tp_get_athlete_settings Get athlete settings: FTP, thresholds, zones, profile. Read tp_get_atp Get Annual Training Plan - weekly TSS targets, training periods, races. Max 90 days. Read tp_get_availability Get availability entries for a date range. Read tp_get_equipment List equipment (bikes, shoes). Read tp_get_events List events in a date range. Read tp_get_fitness Get fitness/fatigue trend (CTL/ATL/TSB). Supports historical date ranges. Read tp_get_focus_event Get the A-priority focus event with goals and results. Read tp_get_libraries List workout library folders. Read tp_get_library_item Get full template details including structure. Read tp_get_library_items List templates in a workout library. Read tp_get_metrics Get health metrics for a date range. Read tp_get_next_event Get the nearest future planned event. Read tp_get_note Get a calendar note by ID. Read tp_get_note_comments Get all comments on a calendar note. Read tp_get_nutrition Get nutrition data for a date range. Read tp_get_peaks Get top performances by type. For comparing PRs over time. Read tp_get_pool_length_settings Get pool length settings. Read tp_get_profile Get athlete profile. Rarely needed - other tools work without it. Read tp_get_weekly_summary Combined view of workouts + fitness for a week. Totals TSS, duration, end-of-week CTL/ATL/TSB. Read tp_get_workout Get workout details by ID. Use after tp_get_workouts. Read tp_get_workout_comments Get comments on a workout. Read tp_get_workout_note Get the private workout note for a workout. Read tp_get_workout_prs Get PRs set during a specific workout. Read tp_get_workout_types List all sport types and subtypes with IDs. Use to find subtype_id for create/update. Read tp_get_workouts List workouts in date range. Query only days needed. Max 90 days. Read tp_list_athletes List athletes available to this account (coach accounts). Read tp_list_notes List calendar notes for a date range. Read tp_refresh_auth Refresh auth by extracting cookie from user Read tp_validate_structure Validate workout interval structure without creating a workout.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about TrainingPeaks-MCP

Can an AI agent delete data through the TrainingPeaks- MCP server? +

Yes. The TrainingPeaks-MCP server exposes 7 destructive tools including tp_delete_availability, tp_delete_equipment, tp_delete_event. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through TrainingPeaks-MCP? +

The TrainingPeaks-MCP server has 26 write tools including tp_add_note_comment, tp_add_workout_comment, tp_copy_workout. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach TrainingPeaks-MCP.

How many tools does the TrainingPeaks- MCP server expose? +

65 tools across 3 categories: Destructive, Read, Write. 32 are read-only. 33 can modify, create, or delete data.

How do I enforce a policy on TrainingPeaks-MCP? +

Register the TrainingPeaks- MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every TrainingPeaks-MCP tool call.

Deterministic rules across all 65 TrainingPeaks-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TRAININGPEAKS-MCP →

Instant setup, no code required.

65 TrainingPeaks-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.