MCP 服务器

WHOOP MCP

Privacy-first, unofficial WHOOP MCP server for AI health, sleep, recovery, and performance agents.

README

<h1 align="center">WHOOP MCP</h1>

<h3 align="center"> Give your AI agent your WHOOP recovery, sleep, strain and HRV — without copy-pasting from the app.<br> Local-first MCP server — <strong>tokens never leave your machine</strong>. </h3>

⚡ One-command install with Delx Wellness for Hermes: npx -y delx-wellness-hermes setup — preconfigures this connector and the full Delx Wellness stack in a dedicated Hermes profile.

Or wire it standalone into Claude Desktop / Cursor / ChatGPT Desktop — see the install section below. Runnable examples live in the Delx Agent Workbench.

Public proof: WHOOP MCP is tracked in the Delx Open Source Growth Snapshot alongside downloads, stars and next-action priorities. If it saves you OAuth and MCP setup time, star this repo so other recovery-focused agent builders can find it faster.

First useful prompt: Use whoop_connection_status, then whoop_daily_summary, then give me a 5-line operating brief for today.

Local-first MCP server that connects AI agents to your WHOOP recovery, sleep, strain and HRV data.

Unofficial project. Not affiliated with, endorsed by or supported by WHOOP, Inc. WHOOP is a trademark of its respective owner. Use this only with your own WHOOP account and in line with WHOOP's Developer Terms.

Built by David Mosiah for people who use Claude, Cursor, Hermes, OpenClaw or other MCP-compatible agents to think about training, sleep and recovery — without copy-pasting numbers from the WHOOP app.

Part of Delx Wellness, a registry of local-first wellness MCP connectors.

Prior work and credits

WHOOP MCP Unofficial builds on prior WHOOP MCP groundwork by Shashank Mishra, including the OAuth/WHOOP API direction and the earlier MIT-licensed whoop-ai-mcp package (source). This project extends that foundation with local-first setup, privacy audits, dual transport, agent manifests, summaries, caching, registry metadata and Delx Wellness hub integration.

If this connector helps your agent workflow, please star the repo. Stars make the project easier for other AI builders to discover and help Delx keep shipping local-first wellness infrastructure.

Why this exists

WHOOP gives you rich physiology — recovery score, HRV, sleep stages, strain — but it lives behind an OAuth API and a closed app. Bringing it into your AI agent today means writing the OAuth dance yourself, storing tokens safely, normalizing responses and handling pagination.

This package does all of that locally, exposes WHOOP through the Model Context Protocol, and lets any MCP-compatible agent read your WHOOP context with one config snippet. Tokens never leave your machine.

Setup in 60 seconds

You'll need a WHOOP Developer app (create one here) with redirect URI http://127.0.0.1:3000/callback.

npx -y whoop-mcp-unofficial setup    # interactive: paste client id + secret
npx -y whoop-mcp-unofficial auth     # opens browser, captures the OAuth code
npx -y whoop-mcp-unofficial doctor   # verifies you're ready

Then add this to your MCP client config:

{
  "mcpServers": {
    "whoop": {
      "command": "npx",
      "args": ["-y", "whoop-mcp-unofficial"]
    }
  }
}

For Claude Desktop, run setup --client claude and the snippet is written for you.

See it before you connect

No WHOOP account yet? Call whoop_demo — it returns realistic synthetic recovery, sleep and strain payloads (tagged is_demo: true) so your agent learns the data contract before any OAuth. Just ask:

Call whoop_demo and explain what my daily WHOOP signals would look like.

Default (markdown) output:

# WHOOP Demo

- **is_demo**: true
- **recovery_score**: 67
- **sleep_performance**: 88
- **recommendation**: Moderate recovery + adequate sleep — green light for moderate intensity training. Consider a magnesium-rich meal to keep HRV trending up.

With response_format=json you get the full shape the live tools return:

{
  "is_demo": true,
  "sample": {
    "whoop_daily_summary": {
      "date": "2026-05-29",
      "recovery": { "score": 67, "hrv_ms": 58, "resting_heart_rate": 52 },
      "sleep": { "performance": 88, "duration_min": 462, "efficiency": 91, "stages": { "rem_min": 96, "deep_min": 78 } },
      "strain": { "day_strain": 11.2, "max_heart_rate": 162 },
      "workouts": 1
    },
    "whoop_wellness_context": {
      "window": "last_24h", "recovery_score": 67, "recovery_band": "moderate",
      "sleep_performance": 88, "day_strain": 11.2, "hrv_ms": 58, "resting_heart_rate": 52,
      "recommendation": "Moderate recovery + adequate sleep — green light for moderate intensity training. Consider a magnesium-rich meal to keep HRV trending up."
    },
    "whoop_list_recoveries": {
      "count": 3,
      "records": [
        { "date": "2026-05-29", "score": 67, "hrv_ms": 58 },
        { "date": "2026-05-28", "score": 72, "hrv_ms": 61 },
        { "date": "2026-05-27", "score": 54, "hrv_ms": 49 }
      ]
    }
  }
}

Once you finish OAuth setup below, whoop_daily_summary, whoop_wellness_context and whoop_list_recoveries return this same shape with your live WHOOP data.

Record a real demo safely

After OAuth is connected, generate a privacy-sanitized transcript for README demos, issue updates or agent evals:

npx -y whoop-mcp-unofficial demo-capture \
  --output whoop-recovery-demo.redacted.json \
  --markdown whoop-recovery-demo.redacted.md \
  --assert-sanitized

demo-capture runs the same readiness path an agent should use: whoop_connection_status shape first, then whoop_daily_summary, then a short recovery-aware prompt. It fails closed when setup is incomplete and the sanitizer blocks OAuth secrets, local token paths, raw payloads, exact recovery numbers and exact sleep details. The committed redaction contract is a fixture-only sample; real captures should be reviewed before publishing.

Try it with your agent

Three things to ask first:

Use whoop_connection_status to check setup, then run whoop_daily_summary.
Give me a 5-line operating brief for today.

Call whoop_weekly_summary with response_format=json. Identify the top
bottleneck and give me a sleep + training plan for next week.

Use the whoop_daily_performance_coach prompt. Focus on whether I should train
hard today.

Data availability

This package uses the official WHOOP OAuth API (v2). It does not access raw device sensor streams.

Data	Available	Notes
Recovery score, HRV, RHR, SpO2, skin temp	✓	When WHOOP returns a scored recovery
Sleep sessions + stages + performance	✓	All scored sleep records
Cycles + day strain + kilojoules	✓	Physiological cycles
Workouts + sport + heart-rate zones	✓	All recorded workouts
Profile + body measurements	✓	Height, weight, max HR
Continuous heart-rate / device telemetry	—	Not exposed by WHOOP's public API
Live BLE heart-rate listening	—	This package is not a Bluetooth listener

When this README says raw, it means the upstream WHOOP API JSON for a supported endpoint — not raw sensor samples.

Tools

Start with these:

whoop_demo — realistic synthetic recovery/sleep/strain payloads, no OAuth needed (see See it before you connect)
whoop_connection_status — verify local setup before calling WHOOP
whoop_data_inventory — inventory supported data domains, scopes, privacy modes and recommended first calls without calling WHOOP APIs.
whoop_daily_summary — readiness, sleep, load and action candidates for today
whoop_weekly_summary — scorecard, comparison vs prior week, next-week plan

Auth & diagnostics

whoop_capabilities, whoop_agent_manifest, whoop_privacy_audit, whoop_cache_status
whoop_get_auth_url, whoop_exchange_code, whoop_revoke_access

Profile

whoop_get_profile, whoop_get_body_measurements

Collections (paginated, with start/end filters and privacy-mode override)

whoop_list_recoveries, whoop_list_sleeps, whoop_list_cycles, whoop_list_workouts

Common collection params: start, end, limit (max 25), next_token, all_pages, max_pages, response_format (markdown/json), privacy_mode (summary/structured/raw).

Single records by id

whoop_get_cycle, whoop_get_sleep, whoop_get_workout
whoop_get_cycle_sleep, whoop_get_cycle_recovery

Prompts

whoop_daily_performance_coach — practical daily plan from today's signals
whoop_weekly_training_review — week comparison + next-week plan
whoop_sleep_recovery_investigator — investigate sleep ↔ recovery patterns

Each accepts timezone (IANA, default UTC).

Resources

whoop://capabilities
whoop://summary/daily, whoop://summary/weekly
whoop://latest/recovery, whoop://latest/sleep, whoop://latest/cycle

Privacy & security

OAuth tokens are stored in ~/.whoop-mcp/tokens.json with 0600 permissions and are never returned by tools.
Refresh-token rotation uses a lock file to avoid concurrent refresh races.
whoop_revoke_access is the only destructive tool — it deletes local tokens and revokes the grant.
WHOOP_PRIVACY_MODE defaults to structured. Raw WHOOP API payloads are opt-in via raw mode or per-call override.
demo-capture redacts demo transcripts before writing anything intended for docs or issues.
The MCP client never sees access or refresh tokens.
This is not medical advice. The server exposes user-authorized data for personal AI workflows, not diagnosis or treatment.

Configuration

setup writes most of these into ~/.whoop-mcp/config.json (0600). Manual env override is supported:

WHOOP_CLIENT_ID=…
WHOOP_CLIENT_SECRET=…
WHOOP_REDIRECT_URI=http://127.0.0.1:3000/callback

# Optional
WHOOP_SCOPES="read:recovery read:cycles read:workout read:sleep read:profile read:body_measurement"
WHOOP_PRIVACY_MODE=structured        # summary | structured | raw
WHOOP_CACHE=sqlite                   # optional read-through cache
WHOOP_TOKEN_PATH=~/.whoop-mcp/tokens.json
WHOOP_CACHE_PATH=~/.whoop-mcp/cache.sqlite

Hermes / remote setup

npx -y whoop-mcp-unofficial setup --client hermes --no-auth
npx -y whoop-mcp-unofficial auth                       # run locally if browser auth is needed
npx -y whoop-mcp-unofficial doctor --client hermes
hermes mcp test whoop

After Hermes config changes, use /reload-mcp or hermes mcp test whoop. Don't restart the gateway for normal data access.

If browser OAuth has to happen on a different machine than Hermes, run auth locally and copy ~/.whoop-mcp/tokens.json to the server with chmod 600.

Requirements

Node.js 20+
A WHOOP Developer app with redirect URI http://127.0.0.1:3000/callback

Default OAuth scopes:

read:recovery read:cycles read:workout read:sleep read:profile read:body_measurement

Development

git clone https://github.com/davidmosiah/whoop-mcp.git
cd whoop-mcp
npm install
npm test
npm run build

Test with MCP Inspector:

npx @modelcontextprotocol/inspector node dist/index.js

Optional local HTTP transport:

WHOOP_MCP_TRANSPORT=http WHOOP_MCP_PORT=3000 node dist/index.js
curl http://127.0.0.1:3000/health

Docs

Provider	Package	Repo
WHOOP	`whoop-mcp-unofficial`	whoop-mcp
Oura	`oura-mcp-unofficial`	ouramcp
Garmin	`garmin-mcp-unofficial`	garminmcp
Strava	`strava-mcp-unofficial`	strava-mcp
Fitbit	`fitbit-mcp-unofficial`	fitbitmcp
Withings	`withings-mcp-unofficial`	withingsmcp
Apple Health	`apple-health-mcp-unofficial`	apple-health-mcp
Polar	`polar-mcp-unofficial`	polarmcp
Nourish (nutrition)	`wellness-nourish`	wellness-nourish

📧 Contact & Support

📨 support@delx.ai — general questions, integration help, partnerships
🐛 Bug reports / feature requests — GitHub Issues
🐦 Updates — @delx369 on X
🌐 Site — wellness.delx.ai

License

MIT — see LICENSE.

Disclaimer

This software is provided as-is. It is not a medical device, does not provide medical advice, and should not be used for diagnosis or treatment. Always consult qualified professionals for medical concerns.