Get a patient
AI agents call get_patient_whoop_sleep_data to retrieve information from Intelligent Medical Assistant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it queries and retrieves patient sleep data without side effects. Severity is high rather than medium because it accesses sensitive protected health information (PHI) including sleep biometrics, which are personal medical records. An AI agent with unrestricted access could retrieve extensive health profiles across multiple patients.
From the tool's definition Tool name 'get_patient_whoop_sleep_data' and description 'Get a patient' indicate data retrieval. The server description confirms this is part of 'automated medical tools' for tracking patient biometrics including 'sleep patterns.' The function retrieves but…
Attacks that exploit this kind of access
Get a patient. It is categorised as a Read tool in the Intelligent Medical Assistant MCP Server, which means it retrieves data without modifying state.
Register the Intelligent Medical Assistant MCP server in PolicyLayer and add a rule for get_patient_whoop_sleep_data: 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 Intelligent Medical Assistant. Nothing to install.
get_patient_whoop_sleep_data 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_patient_whoop_sleep_data 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_patient_whoop_sleep_data. 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_patient_whoop_sleep_data is provided by the Intelligent Medical Assistant MCP server (sp2learn/medical-mcp-server). 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 →