Whoop Mcp Server

io.github.rajdeepmondaldotcomPublished by GitHub account rajdeepmondaldotcomv0.0.12Updated Oct 24, 2026

WHOOP recovery, sleep, strain, and workouts for any AI. Analysis tools, demo mode, fast setup.

VerifiedSTDIODesktop onlyLocation & LifestyleData & Analytics

Overview

AI-generated overview

A local MCP server that connects WHOOP recovery, sleep, strain and workout data to an AI assistant, computing trends and correlations for plain-English health Q

What you can do
Retrieve WHOOP records: sleeps, workouts, cycles, recoveries, profile and legacy activity mappings, with optional raw data and week grids. Analyze health: daily summaries, health overview, recovery and strain trends, correlations, period comparisons and personal records. Export full collection history to local JSON and CSV files. Check connection status and start the WHOOP account authorization flow. Serve ChatGPT-style search and fetch tools plus ready-made prompts for readiness, weekly review, sleep coaching and training planning.
When to use it
Useful when you want an assistant to answer questions about your own WHOOP data, such as whether to train hard, what affects recovery, or how this quarter compares with earlier periods, instead of reading charts yourself.
Requirements
Runs locally via uv or pipx (Python package). Needs a WHOOP account and membership, plus an MCP client such as Claude Desktop, Claude Code, Cursor, Windsurf, VS Code or ChatGPT. Setup creates your own free WHOOP developer app and requires WHOOP_CLIENT_ID and WHOOP_CLIENT_SECRET, stored locally. Network access to api.prod.whoop.com. WHOOP_MCP_DEMO=1 serves generated demo data without an account.
Before you install
Health data is sensitive: aggregates like trends and correlations can reveal more than single records, so connect only AI clients you trust. The ChatGPT tunnel setup uses no authentication, meaning anyone with the URL can read your health data; keep it private and short-lived. Setup writes and backs up client configuration files and stores OAuth tokens locally. Export writes local files. Read-only against WHOOP otherwise.

Installation

In SourceWeft

  1. Open Whoop Mcp Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

whoop-mcp-server

Your WHOOP shows you charts. It can't answer "should I train hard today" or "what actually hurts my recovery". This server can.

It connects your WHOOP data to Claude, ChatGPT, and any MCP client. You ask in plain English. It computes the answer from your own records and lets the AI explain it.

[CI] [Python 3.10+] [License: MIT] [MCP] [Glama]

text
You: should I train hard today?
AI:  Recovery 81% (green). HRV trending up. Sleep debt cleared.     Your 7-day load is 0.94x your 28-day base.     You are conditioned for more.

Runs on your machine. Read-only. The only network peer is api.prod.whoop.com. No telemetry. MIT.

What you need

  • A WHOOP account. Any membership works.
  • uv or pipx, to install one command line tool.
  • An MCP client: Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, or ChatGPT.

One constraint to know before you start. WHOOP has no shared developer app, so during setup you create your own free one. It takes about two minutes of clicking, and it is the reason this is private by design: your tokens belong to your app, on your machine, and your health data never routes through anyone else's server. Including mine.

Set it up

Install the tool:

bash
uv tool install whoop-mcp-server

(pipx install whoop-mcp-server works the same.)

Then run the one command that does everything:

bash
whoop-mcp-server setup

Here is what happens, in order, so nothing surprises you:

  1. Your WHOOP app. The wizard opens WHOOP's developer dashboard and tells you exactly what to click: create a team, create an app, enable every scope including offline, set the redirect URL to exactly http://localhost:8765/callback. The form requires a privacy policy URL. Use this repo's: https://github.com/rajdeepmondaldotcom/whoop-mcp-server/blob/main/PRIVACY.md. Copy the Client ID and Secret, paste them into the terminal. They're stored locally with 0600 permissions.

  2. Authorize. Your browser opens WHOOP's consent screen. Approve it. Tokens land in ~/.whoop-mcp and refresh themselves from then on. You never do this again.

  3. Proof. The wizard makes a live API call and prints your actual latest recovery. If anything is misconfigured, you find out here, in the terminal, not later in a chat window.

  4. Your clients. It detects Claude Desktop, Cursor, Windsurf, VS Code, and Claude Code, and writes their configs for you. Existing config is backed up before any edit. If Claude Desktop is running, the wizard asks to quit it first, because Desktop silently overwrites config edits made while it's open. Then it launches the configured command once and confirms the server answers. "Done" means verified, not hopeful.

Restart your client. Ask it: "How did I sleep last night?" Then ask the better question: "Give me the full picture of my health this quarter."

Two useful asides. If you want to see the tools work before connecting anything, whoop-mcp-server serve --demo serves 150 days of realistic generated data through the same pipeline. And if anything misbehaves later, whoop-mcp-server doctor names what's wrong and the fix.

What you can ask

24 tools cover every public user-readable endpoint in WHOOP's API, plus the analysis layer that turns records into answers.

AskTool behind it
"Give me the full picture of my health"get_health_overview: status, trends, training load, records, and correlations in one call
"How am I doing today?"get_daily_summary: recovery, sleep, strain, workouts for any day
"What actually affects my recovery?"get_correlations: strain vs next-morning recovery, sleep vs recovery, with plain readings
"Am I overtraining?"get_strain_trends: acute vs chronic load, per-sport breakdown
"Is my HRV improving?"get_recovery_trends: direction, confidence, unusual days
"Show my overnight heart rate curve"get_sleep_stream: minute-level HR and skin temp, lowest point and when; include_raw=true keeps WHOOP's untouched stream
"This month vs last month?"compare_periods: every metric, improved or declined
"My records this year?"get_personal_records: bests, worsts, green streaks
"Export everything"export_data: full collection history to local JSON and CSV, with raw records by default
Week grids, raw records, profileget_weekly_report, get_sleeps/workouts/cycles/recoveries, by-id tools with include_raw, get_profile(include_raw=true)
"I have an old WHOOP activity id"get_activity_mapping: map a legacy v1 activity id to its v2 UUID
Connection troubleget_connection_status, connect_whoop_account

Dates are plain English everywhere: yesterday, last 30 days, this week, 2 years ago, 2026-05.

ChatGPT's required search and fetch tools are implemented too, plus 4 resources and 4 ready-made prompts (morning_readiness, weekly_review, sleep_coach, training_planner).

More questions worth asking: docs/PROMPTS.md.

Works with

ClientSetup
Claude Desktopwhoop-mcp-server setup configures it for you. No terminal at all: download whoop-mcp-server.mcpb from the latest release and open it (needs uv installed; demo mode is a toggle in its settings)
Claude Codeclaude mcp add whoop -- whoop-mcp-server serve (setup offers this too)
Cursorauto via setup, or [Install in Cursor]
Windsurfauto via setup
VS Codeauto via setup, or [Install in VS Code]
ChatGPTremote connector, see below
Dockerdocker build -t whoop-mcp-server . && docker run -i --rm -e WHOOP_MCP_DEMO=1 whoop-mcp-server (mount ~/.whoop-mcp for real data)
Any MCP clientcommand: whoop-mcp-server with args: ["serve"]. Inspector: npx @modelcontextprotocol/inspector whoop-mcp-server serve
ChatGPT setup

ChatGPT connects to remote MCP servers, so expose the HTTP transport and tunnel it:

bash
whoop-mcp-server serve --transport http --port 8000    # endpoint: /mcpngrok http 8000

Then in ChatGPT: Settings, Apps & Connectors, Advanced settings, enable Developer mode, create a connector with https://<your-tunnel>/mcp and no auth.

Be careful here: a no-auth tunnel means anyone with the URL can read your health data. Keep the URL private and the tunnel short-lived. Claude's stdio setup never exposes anything.

Why the answers hold up

The model is maybe 20% of this product. The other 80% is making the numbers right. Models are bad at arithmetic over 90 days of records, so this server computes first and lets the model explain.

  • Trend lines are fit to date-sorted series. WHOOP returns records newest-first. Fit arrival order instead and every trend reads backwards.
  • Direction respects what the metric means. Rising HRV is improvement. Rising resting heart rate is not.
  • Records land on calendar days using their own timezone offset. A sleep belongs to the morning you woke up, even when you travel.
  • WHOOP rotates both OAuth tokens on every refresh. Refreshes here are serialized, saved before use, and shared across concurrent requests. Re-running auth rescues a live server without a restart.
  • The client honors WHOOP's rate-limit headers, retries with backoff, and caps pagination. When a result is truncated or approximate, the output says so instead of pretending it's complete.

What it can't do: WHOOP's public API has no endpoints yet for Peak features like the stress monitor and healthspan. When WHOOP ships them, they land here. The overnight sensor stream isn't enabled for every account, and the tool reports that instead of failing. Bulk export intentionally fetches the collection endpoints; raw sleep streams are available per sleep with get_sleep_stream(include_raw=true).

105 tests, all offline against a faked WHOOP API. CI on Python 3.10 to 3.13.

CLI

text
whoop-mcp-server setup     Guided setup: app, authorize, auto-configure clientswhoop-mcp-server serve     Run the server (--demo, --transport stdio|http|sse, --host, --port)whoop-mcp-server status    Config and token statewhoop-mcp-server doctor    Diagnose setup and connectivitywhoop-mcp-server auth      Scriptable OAuth flowwhoop-mcp-server logout    Delete tokens (--revoke also revokes at WHOOP)

Configuration

Nothing required after whoop-mcp-server setup. Overrides, in priority order: process env, ./.env, ~/.whoop-mcp/.env, ~/.whoop-mcp/config.json.

VariableDefaultPurpose
WHOOP_CLIENT_ID / WHOOP_CLIENT_SECRETnoneWHOOP app credentials
WHOOP_REDIRECT_URIhttp://localhost:8765/callbackMust exactly match the dashboard
WHOOP_MCP_DEMOoff1 serves demo data (same as --demo)
WHOOP_MCP_DIR~/.whoop-mcpTokens, config, exports
WHOOP_MCP_TZsystem zoneIANA timezone for "today" and week bounds
WHOOP_MCP_CACHE_TTL / WHOOP_MCP_TIMEOUT60 / 30Seconds
WHOOP_MCP_LOG_LEVELINFOLogs go to stderr. stdout belongs to MCP
WHOOP_ACCESS_TOKENnoneStatic token for testing, no refresh

Privacy

Read-only against WHOOP. Tokens stored locally with 0600 permissions. The only writes are local files you ask for (export_data) and the OAuth flow you trigger. One thing worth knowing: aggregates like trends and correlations can reveal more about you than single records. Connect this only to AI clients you trust with health data. Full policy: PRIVACY.md. Vulnerabilities: SECURITY.md.

Contributing

bash
uv venv && uv pip install -e ".[dev]" && pytest && ruff check .

The whole test suite runs offline. CONTRIBUTING.md lists the invariants that keep the data honest. The short version of the architecture: client.py talks to WHOOP, transform.py cleans the records, summaries.py and analytics.py do the math, server.py exposes the tools. oauth.py and tokens.py own auth. demo.py is the generated account.

Troubleshooting

SymptomFix
"WHOOP authorization required"whoop-mcp-server setup, or ask your AI to connect your WHOOP account
Redirect fails after consentThe dashboard redirect URI must be exactly http://localhost:8765/callback
403 missing scopeEnable all read scopes plus offline on the app, then re-run whoop-mcp-server auth
Tools missing in a clientRe-run whoop-mcp-server setup, then fully restart the client
No recovery shown todayWHOOP scores it after you wake and sync. The summary says so
Sleep stream "not available"WHOOP doesn't expose it for every account. Nightly summaries still work
Anything elsewhoop-mcp-server doctor, or get_connection_status from chat, or open an issue

License

MIT. See LICENSE. Not affiliated with or endorsed by WHOOP. WHOOP is a trademark of WHOOP, Inc.

Source: README.md at commit e7a4d5d

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.0.12LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts