Return a risk-aware summary for a specific patient, including trends and outstanding gaps.
AI agents call patient_profile to retrieve information from HomeCare Cohort MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates clinical information about a patient to generate a summary report. While it operates on sensitive healthcare data (patient profiles), it performs no write operations, does not execute external commands, does not delete data, and does not involve financial transactions. The risk is inherent to accessing protected health information rather than the action performed.
From the tool's definition Tool description states 'Return a risk-aware summary for a specific patient, including trends and outstanding gaps.' The verb 'Return' and the nature of the operation (summarizing existing patient data) indicate data retrieval with no modification or side…
Attacks that exploit this kind of access
Return a risk-aware summary for a specific patient, including trends and outstanding gaps. It is categorised as a Read tool in the HomeCare Cohort MCP MCP Server, which means it retrieves data without modifying state.
Register the HomeCare Cohort MCP server in PolicyLayer and add a rule for patient_profile: 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 HomeCare Cohort MCP. Nothing to install.
patient_profile 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 patient_profile 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 patient_profile. 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.
patient_profile is provided by the HomeCare Cohort MCP server (nasir0md/homecare-cohort-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 →