Get care plans for a patient
AI agents call get_patient_careplans 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 care plan data from an EMR (Cerner/Epic via FHIR), which is a read-only query with no side effects. However, severity is elevated to 'high' because it accesses sensitive protected health information (PHI) under HIPAA; unauthorized or erroneous retrieval/disclosure of care plans could harm patient privacy and inform incorrect clinical decisions.
From the tool's definition Tool name 'get_patient_careplans' uses 'get' verb and description states 'Get care plans for a patient'—purely a retrieval operation with no modification, deletion, or execution.
Attacks that exploit this kind of access
Get care plans for a 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_patient_careplans: 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_patient_careplans 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_careplans 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_careplans. 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_careplans 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 →