Get recovery analysis with HRV, RHR, and trends.
AI agents call whoop_get_recovery to retrieve information from WHOOP MCP Server for Poke without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves recovery metrics (HRV, RHR, trends) from the WHOOP fitness platform with no side effects, reversals, or external state changes. It is purely a data query operation analogous to 'get' or 'fetch' patterns.
From the tool's definition Tool name 'whoop_get_recovery' and description 'Get recovery analysis' indicate data retrieval without modification. The server context confirms this is a fitness data query interface ('enabling natural language queries for recovery scores, sleep analysis').
Attacks that exploit this kind of access
Get recovery analysis with HRV, RHR, and trends. It is categorised as a Read tool in the WHOOP MCP Server for Poke MCP Server, which means it retrieves data without modifying state.
Register the WHOOP MCP Server for Poke MCP server in PolicyLayer and add a rule for whoop_get_recovery: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches WHOOP MCP Server for Poke. Nothing to install.
whoop_get_recovery is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the whoop_get_recovery rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for whoop_get_recovery. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
whoop_get_recovery is provided by the WHOOP MCP Server for Poke MCP server (kabirrgrover/whoop-mcp-poke). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →