AI agents call get_recovery to retrieve information from Whoop without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves fitness and health metrics from the Whoop service without modifying, deleting, or executing external operations. It presents no side effects beyond querying existing data. Severity is low because misuse would only expose personal health data already accessible to the account holder, with minimal blast radius.
From the tool's definition Tool name begins with 'get_' and description states 'Get recovery scores'; the description indicates data retrieval only (HRV, resting heart rate, sleep performance metrics).
Attacks that exploit this kind of access
Get recovery scores including HRV, resting heart rate, sleep performance,. It is categorised as a Read tool in the Whoop MCP Server, which means it retrieves data without modifying state.
Register the Whoop MCP server in PolicyLayer and add a rule for 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. Nothing to install.
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 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 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.
get_recovery is provided by the Whoop MCP server (saadh05/whoop-mcp). 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 →