// SCAN REPORT

Pelaris

37 tools. 20 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

20 can modify or destroy data

17 read-only

37 tools total

Community server · catalogue entry verified 03/07/2026

How to control Pelaris ↓

TOOL MAP

What Pelaris exposes to your agents

Read (17) Write / Execute (18) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Pelaris tools

Destructive · High delete_session This tool permanently removes training session records from the user's fitness coaching system. Destructive · High delete_sessions This tool permanently removes training session records from the fitness platform without recovery option. Write · Medium complete_intake The tool appears to initialize or complete an athlete intake form/profile, which is a reversible data creation operation. Write · Low create_planned_session This tool creates a new workout session record in the user's calendar.

20 of Pelaris's 37 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Pelaris

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

Deny destructive operations

{
  "delete_session": {
    "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

{
  "complete_intake": {
    "limits": [
      {
        "counter": "complete_intake_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_active_program": {
    "limits": [
      {
        "counter": "get_active_program_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 Pelaris — 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 PELARIS →

Instant setup, no code required.

FULL CATALOGUE

All 37 Pelaris tools

DESTRUCTIVE 2 tools

Destructive delete_session Delete a planned training session. Completed and Strava-imported sessions cannot be deleted. Destructive delete_sessions Delete multiple planned training sessions at once (max 20). Returns per-session success/failure.

WRITE 18 tools

Write complete_intake Complete the athlete Write create_planned_session Schedule a future workout session with target exercises. The session will appear in your training calendar rea Write daily_check_in Log how you Write generate_program Generate a complete training program tailored to your goals and enrol it as your active program. Covers short Write generate_weekly_plan Deprecated: prefer generate_program, which enrols a scored, trainable program. Generate a weekly training plan Write log_completed_session Log a completed workout retroactively with exercises, RPE, feedback, and coach notes. Prevents duplicate entri Write log_workout Record a completed workout with exercises, RPE, and how you felt. Duplicate entries are automatically prevente Write manage_goals Create, update, complete, or list your training goals. Supports race events, body composition targets, and per Write manage_program Archive a training program. Use get_program_status to view programs first. Write modify_training_session Adjust a planned session — reduce volume, change intensity, swap exercises, or reschedule to a different date. Write record_benchmark Record a new personal best or benchmark result. Previous values are saved to history so you can track progress Write record_injury Log an injury or pain point so your training plan adapts automatically. Returns a coaching note about how sess Write send_feedback Share feedback about the coaching experience to help improve tool quality and accuracy. Write swap_exercise Find alternative exercises with rationale, or swap an exercise in a planned session. Returns 3 suggestions bas Write update_profile Update your training preferences — equipment, available days, session duration, experience level, and more. Write update_session Update an existing session with corrected or additional data — title, focus, duration, status, RPE, feedback, Write write_pipeline_item Create or update a content pipeline item. Provide an ID to update, omit to create. Write write_research Write or update a research cache entry. Creates a new document or updates an existing one by ID.

READ 17 tools

Read get_active_program View your current training programs with progress, phase, weekly structure, and session details. Read get_benchmarks View your performance benchmarks — current values, trends, and progress over time. Read get_body_analysis View your latest body composition data — measurements, ratios, archetype, and changes since your last analysis Read get_coach_insight Get personalised coaching observations based on your recent training — consistency, fatigue, goal progress, an Read get_feedback_item Get a single feedback entry by ID. PII is automatically scrubbed. Read get_generation_status Check the status of a training plan generation job. Returns progress through pipeline stages and session count Read get_onboarding_status Check your account setup progress — intake completion, sport selection, program creation, and device connectio Read get_pipeline_item Get a single content pipeline item by ID. Read get_program_status View your current active training programs or browse your full program history. Read get_research Query research cache by topic. Returns cached research content, sources, and metadata. Read get_session_details View the full details of a workout session — exercises, sets, reps, weights, completion status, and feedback. Read get_training_overview View your complete training snapshot — active programs, recent sessions, check-in data, goals, and progress at Read get_user_stats Get aggregate user statistics (counts only). No individual profile data is returned — privacy by design. Read get_weekly_debrief View your weekly training summary — session completion, highlights, areas for improvement, and next week Read list_feedback List user feedback entries. PII is automatically scrubbed from the response. Read list_pipeline_items List content pipeline items, optionally filtered by status or type. Read search_training_resources Search the curated library of coaching articles, videos, and guides. Find resources by topic, sport, or traini

EXPLORE

Related servers

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

FAQ

Questions about Pelaris

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

Yes. The Pelaris server exposes 2 destructive tools including delete_session, delete_sessions. 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 Pelaris? +

The Pelaris server has 18 write tools including complete_intake, create_planned_session, daily_check_in. 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 Pelaris.

How many tools does the Pelaris MCP server expose? +

37 tools across 3 categories: Destructive, Read, Write. 17 are read-only. 20 can modify, create, or delete data.

How do I enforce a policy on Pelaris? +

Register the Pelaris 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 Pelaris tool call.

Deterministic rules across all 37 Pelaris tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PELARIS →

Instant setup, no code required.

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