Get patient
AI agents call get_lab_results to retrieve information from Agent Care MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves patient lab results from medical records with no modification capability. While the blast radius is high due to sensitive PHI (Protected Health Information) exposure, the category is Read because the operation is a data retrieval with no side effects.
From the tool's definition Tool name 'get_lab_results' and context indicating retrieval of patient data from EMRs (Cerner, Epic) via FHIR. Description states 'Get patient' (incomplete but indicates retrieval).
Attacks that exploit this kind of access
Get patient. It is categorised as a Read tool in the Agent Care MCP MCP Server, which means it retrieves data without modifying state.
Register the Agent Care MCP server in PolicyLayer and add a rule for get_lab_results: 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 Agent Care MCP. Nothing to install.
get_lab_results 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_lab_results 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_lab_results. 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_lab_results is provided by the Agent Care MCP server (polya20/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 →