Pelaris (theDonk/pelaris-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 35 tools. No publisher has claimed this listing.

D
Caution
54/100

Pelaris

Connect Pelaris to any MCP-compatible AI assistant for personalised fitness coaching. Plan training programs, log workouts, track benchmarks, manage goals, and get data-driven coaching insights. Supports science-based methodologies including 5/3/1, Pfitzinger, polarised training, and more. OAuth 2.0 authentication with Streamable HTTP transport. Documentation: https://pelaris.io/integrations Web

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

theDonk

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
35 tools verified — handlers match their declared behaviour
11 read-only tools verified — handlers contain no write/delete/exec
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 2 credentials: MCP_BEARER_TOKEN, MCP_JWT_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes35 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

list_feedback

List user feedback entries. PII is automatically scrubbed from the response.

get_feedback_item

Get a single feedback entry by ID. PII is automatically scrubbed.

list_pipeline_items

List content pipeline items, optionally filtered by status or type.

get_pipeline_item

Get a single content pipeline item by ID.

write_pipeline_item

Create or update a content pipeline item. Provide an ID to update, omit to create.

get_user_stats

Get aggregate user statistics (counts only). No individual profile data is returned — privacy by design.

get_research

Query research cache by topic. Returns cached research content, sources, and metadata.

write_research

Write or update a research cache entry. Creates a new document or updates an existing one by ID.

record_injury

Log an injury or pain point so your training plan adapts automatically. Returns a coaching note about how sessions will adjust.

daily_check_in

Log how you're feeling today — readiness, soreness, sleep, and mood. Your coach uses this to adapt upcoming sessions.

create_planned_session

Schedule a future workout session with target exercises. The session will appear in your training calendar ready to track.

delete_session

Delete a planned training session. Completed and Strava-imported sessions cannot be deleted.

delete_sessions

Delete multiple planned training sessions at once (max 20). Returns per-session success/failure.

generate_weekly_plan

Generate a new weekly training plan tailored to your program, goals, and readiness. Sessions are written directly to your calendar.

get_active_program

View your current training programs with progress, phase, weekly structure, and session details.

get_benchmarks

View your performance benchmarks — current values, trends, and progress over time.

get_body_analysis

View your latest body composition data — measurements, ratios, archetype, and changes since your last analysis.

get_coach_insight

Get personalised coaching observations based on your recent training — consistency, fatigue, goal progress, and areas to focus on.

get_generation_status

Check the status of a training plan generation job. Returns progress through pipeline stages and session count when complete.

get_onboarding_status

Check your account setup progress — intake completion, sport selection, program creation, and device connections.

get_program_status

View your current active training programs or browse your full program history.

get_session_details

View the full details of a workout session — exercises, sets, reps, weights, completion status, and feedback.

get_training_overview

View your complete training snapshot — active programs, recent sessions, check-in data, goals, and progress at a glance.

get_weekly_debrief

View your weekly training summary — session completion, highlights, areas for improvement, and next week's focus.

send_feedback

Share feedback about the coaching experience to help improve tool quality and accuracy.

log_completed_session

Log a completed workout retroactively with exercises, RPE, feedback, and coach notes. Prevents duplicate entries automatically.

log_workout

Record a completed workout with exercises, RPE, and how you felt. Duplicate entries are automatically prevented.

manage_goals

Create, update, complete, or list your training goals. Supports race events, body composition targets, and performance milestones.

manage_program

Archive a training program. Use get_program_status to view programs first.

modify_training_session

Adjust a planned session — reduce volume, change intensity, swap exercises, or reschedule to a different date.

record_benchmark

Record a new personal best or benchmark result. Previous values are saved to history so you can track progress over time.

search_training_resources

Search the curated library of coaching articles, videos, and guides. Find resources by topic, sport, or training goal.

swap_exercise

Find alternative exercises with rationale, or swap an exercise in a planned session. Returns 3 suggestions based on movement pattern.

update_session

Update an existing session with corrected or additional data — title, focus, duration, status, RPE, feedback, exercises, or coach notes.

update_profile

Update your training preferences — equipment, available days, session duration, experience level, and more.

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.12.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configALLOWED_ORIGINS
configCF_BASE_URL
configGCP_PROJECT_ID
🔐 secretMCP_BEARER_TOKEN
🔐 secretMCP_JWT_SECRET
configOAUTH_CF_BASE
configOWNERSHIP_VERIFICATION_LOG_ONLY
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

27/35 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

18/35 tools missing one or more hints — list_feedback (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_feedback_item (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_pipeline_items (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +15 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

openWorldHint matches behaviour

1 tool claims openWorldHint=false but make outbound HTTP — generate_weekly_plan → dynamic (line 108)

Either flip openWorldHint to true (acknowledging external reach) or refactor the handler to avoid outbound HTTP. If the only network calls are to a known fixed endpoint that you consider part of the tool itself, document that and keep openWorldHint=false; otherwise true is honest.

Tool inputs are validated

Only 10/35 tool handlers declare input schemas (29%)

Declare an inputSchema with zod/joi/yup on every tool definition.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.0 (high), @modelcontextprotocol/sdk@1.12.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/thedonk/pelaris-mcp-server?variant=verified)](https://m8ven.ai/mcp/thedonk/pelaris-mcp-server)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 865635729553ca2b4c3537988a9fd06b7b3f91c5
code hash: 7f71f208aa95402fbe01a31a324f2981f12c623240ee87c62d32a5a89d1f660f
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client