Your WHOOP data in the assistant, read-only: recovery, sleep, strain, workouts, cycles and body meas
Scored across 13 tools
The WHOOP data tools (whoop_body_measurement, whoop_cycles, whoop_recovery, etc.) are clearly distinct by metric type. The platform tools are mostly distinct, but authenticate and connect both deal with connection - authenticate handles token acquisition while connect checks status and provides URLs, which could cause some initial confusion. Marketplace is a large multi-purpose tool but is well-described.
The WHOOP-specific tools follow a consistent whoop_<noun> pattern (whoop_body_measurement, whoop_cycles, whoop_sleep), but the platform tools mix conventions: single-word nouns (connect, marketplace), camelCase-like snake_case (report_bug, show_version, toolkit_info), and bare verbs (authenticate). This inconsistency makes the naming less predictable.
13 tools is well within the ideal 3-15 range. The WHOOP data tools cover distinct health metrics, and the platform tools cover auth, connectivity, marketplace, version, and status. Each tool has a clear purpose and the count feels proportionate to the server's dual role as an MCP platform manager and WHOOP data provider.
The WHOOP data surface covers body measurements, daily cycles, recovery, sleep, workouts, profile, and account listing - comprehensive read access to WHOOP's core data. The platform side includes authentication, connection status, marketplace operations, bug reporting, version info, and toolkit state, forming a complete lifecycle for both the MCP platform and WHOOP data access.
MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
Inputs: token.
Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
Inputs: no named parameters.
The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/ link that opens without login.
Inputs: limit, query, action, mcp_id, +19 more.
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
Inputs: message (required), context, conversation.
Show the current MCP platform and adapter versions.
Inputs: no named parameters.
Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
Inputs: no named parameters.
Medidas corporais do membro WHOOP: altura (m), peso (kg) e frequência cardíaca máxima. Dados de wearable, não substituem avaliação médica profissional.
Inputs: account.
Ciclos fisiológicos do WHOOP (dia a dia): strain (0-21), calorias (kilojoule), FC média e máxima. Paginado por limit/start/end/next_token; ou passe cycle_ids pra buscar ciclos específicos. Dados de wearable, não substituem avaliação médica profissional.
Inputs: end, limit, start, account, +2 more.
Lista as contas WHOOP vinculadas a este install (account_id, nome, email).
Inputs: account.
Perfil básico do membro WHOOP (user_id, nome, email).
Inputs: account.
Recovery do WHOOP: recovery_score (0-100%), HRV (rmssd), FC de repouso, SpO2, temperatura da pele. Paginado por limit/start/end/next_token; ou passe cycle_ids pra buscar o recovery de ciclos específicos. Dados de wearable, não substituem avaliação médica profissional.
Inputs: end, limit, start, account, +2 more.
Sono do WHOOP: duração, eficiência, performance (%), estágios (leve, REM, profundo), frequência respiratória. Paginado por limit/start/end/next_token; ou passe sleep_ids (UUID) pra registros específicos. Dados de wearable, não substituem avaliação médica profissional.
Inputs: end, limit, start, account, +2 more.
Workouts do WHOOP: esporte, strain, FC média e máxima, zonas de FC, distância e altimetria quando disponíveis. Paginado por limit/start/end/next_token; ou passe workout_ids (UUID) pra registros específicos. Dados de wearable, não substituem avaliação médica profissional.
Inputs: end, limit, start, account, +2 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Read WHOOP recovery, sleep, cycles, workouts and body measurements.
WHOOP recovery, strain, sleep and workouts in Claude via official WHOOP OAuth. Free, open source.
Your swim, bike and run training: readiness, HRV, sleep, workouts and race predictions. Read-only.
Your own cycling data for your AI assistant: rides, power, climbs and routes. Read-only.
Add one secure layer between your agents and this server.