Finds an id of the patient. It is not required to supply both first name and
AI agents call find_patient_id to retrieve information from Cardiovascular Disease without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves patient identifier information based on name parameters. It performs a query operation to locate a patient record without creating, modifying, deleting, or executing code. The action is a simple read/search operation typical of healthcare data lookups.
From the tool's definition Tool name 'find_patient_id' and description 'Finds an id of the patient' indicate a lookup/retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
Finds an id of the patient. It is not required to supply both first name and. It is categorised as a Read tool in the Cardiovascular Disease MCP Server, which means it retrieves data without modifying state.
Register the Cardiovascular Disease MCP server in PolicyLayer and add a rule for find_patient_id: 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 Cardiovascular Disease. Nothing to install.
find_patient_id 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 find_patient_id 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 find_patient_id. 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.
find_patient_id is provided by the Cardiovascular Disease MCP server (jamesvdinh/cardiovascular-disease-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 →