WhoopSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Connect your WHOOP fitness data to Claude Desktop through the Model Context Protocol (MCP)
[](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://modelcontextprotocol.io/) [](https://smithery.ai/server/@RomanEvstigneev/whoop-mcp-server)
Transform your WHOOP fitness data into actionable insights through natural language queries in Claude Desktop. Ask questions about your workouts, recovery, sleep patterns, and more - all while keeping your data secure and private.
🚀 NEW: Try the Smithery hosted version for zero-setup deployment!
✨ Features
🔐 Secure OAuth Integration - Safe WHOOP account connection with encrypted local storage 🏃 Complete Data Access - Workouts, recovery, sleep, cycles, and profile information 🤖 Natural Language Queries - Ask Claude about your fitness data in plain English ⚡ Smart Caching - Optimized performance with intelligent data caching 🛡️ Privacy First - All data stays on your machine, never sent to third parties 🔄 Auto Token Refresh - Seamless experience with automatic authentication renewal
🚀 Quick Start
🎯 Choose Your Deployment Method
Option A: Smithery Hosted (Recommended for beginners)
- ✅ Zero installation complexity
- ✅ Automatic updates and maintenance
- ✅ Enterprise-grade hosting
- ➡️ Get started with Smithery
Option B: Local Installation (Advanced users)
- ✅ Full control and privacy
- ✅ No external dependencies
- ✅ Customize and extend
- ➡️ Continue with local setup below
📦 Local Installation
1. Prerequisites
- Python 3.8+
- Claude Desktop
- Active WHOOP account
2. Installation
3a6d04f28bdcOBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add whoop-mcp-server-smithery -- npx -y [email protected]
{
"mcpServers": {
"whoop-mcp-server-smithery": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (7)
6 read · 0 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
clear_whoop_cache | destructive | Clear all cached WHOOP data to force fresh API calls |
get_whoop_auth_status | read | Get WHOOP authentication status and connection info |
get_whoop_cycles | read | Get WHOOP physiological cycle data (daily summaries) with optional date range and limit |
get_whoop_profile | read | Get WHOOP user profile information including name and basic details |
get_whoop_recovery | read | Get WHOOP recovery data with optional date range and limit |
get_whoop_sleep | read | Get WHOOP sleep data with optional date range and limit |
get_whoop_workouts | read | Get WHOOP workout data with optional date range and limit |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
clear_whoop_cache
@modelcontextprotocol/sdk, zod, @smithery/cli, @types/node, typescript
pytest, pytest-cov, pytest-asyncio, pytest-mock, black, isort, flake8, mypy
mcp, httpx, pydantic, python-dotenv, cryptography, typing-extensions, requests
@modelcontextprotocol/sdk, zod, @smithery/cli, @types/node, typescript
Gates applied: no_behavioural_pass.
3a6d04f28bdcfull audit observations/trust-audit/mcp-server/romanevstigneev__whoop-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 3a6d04f28bdc | SAFE | B | 89 | first audit |
Questions
What tools does Whoop expose?
7 in total: 6 read-only, 0 that write, and 1 that can delete or overwrite (clear_whoop_cache). Every one is listed on this page with its risk.
Is Whoop safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Whoop need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (3a6d04f28bdc), read on 2026-10-09. The repository is watched and re-audited when it changes.