AI agents call get_patient_procedures to retrieve information from AgentCare without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical procedure records from a patient's medical record. While it poses no direct data modification risk, the sensitivity is elevated to 'medium' severity due to the nature of the data (protected health information under HIPAA). Exposure to an AI agent could result in unauthorized disclosure of sensitive medical procedures, though the tool itself cannot modify or delete records.
From the tool's definition Tool name and description indicate data retrieval: 'Get procedures performed on a patient' with no language suggesting modification, deletion, or execution of operations. The verb 'Get' and context of FHIR/EMR data access indicate a read operation.
Attacks that exploit this kind of access
Get procedures performed on a patient. It is categorised as a Read tool in the AgentCare MCP Server, which means it retrieves data without modifying state.
Register the AgentCare MCP server in PolicyLayer and add a rule for get_patient_procedures: 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 AgentCare. Nothing to install.
get_patient_procedures 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_procedures 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_procedures. 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_procedures is provided by the AgentCare MCP server (kartha-ai/agentcare-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 →