Model Context Protocol (MCP) server for integrating with WHOOP fitness and health API
Server has 6 tools with basic descriptions and minimal parameter documentation. All tools accept an optional 'date' parameter but lack type constraints, format specifications, and validation guidance. Descriptions are present but generic (avg ~60 chars, below 194-char baseline). No output schemas documented. Error handling returns plain text without recovery guidance. Tools lack idempotency hints and composition support. No tool annotations (readOnlyHint, etc.). Parameter descriptions do not explain format (YYYY-MM-DD) or default behavior clearly enough for LLM reasoning.
Test tool to verify MCP server is working.
Get biological age and pace of aging metrics.
Get comprehensive Whoop overview data for a specific date.
Get recovery analysis with HRV, RHR, and trends.
Get detailed sleep analysis and performance metrics.
Get strain analysis with heart rate zones and activities.
No output schemas documented. Tools return plain text strings without structured field definitions. LLMs cannot plan downstream calls or extract typed data.
Parameter 'date' lacks format specification and validation guidance. Description says 'optional, defaults to today' but does not state YYYY-MM-DD is required, what happens if format is wrong, or how the default is applied.
Error responses return plain text ('Error fetching Whoop overview data: {error_msg}') without recovery guidance. LLM cannot determine if error is retryable, user-fixable, or fatal.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 52 | 2026-07-28+ | v2 |
No tool annotations (readOnlyHint, idempotentHint). All tools are read-only but lack explicit hints. Agents cannot infer safety properties.
Credentials (WHOOP_EMAIL, WHOOP_PASSWORD) loaded from environment but no documentation of secret injection pattern or audit trail. No permission gates or scope declarations.