Get patient's medications
AI agents call get_patient_medications to retrieve information from FHIR Careplan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves medication information for a patient, which is a read-only query operation. While the sensitivity is medium due to accessing protected health information (PHI) under HIPAA/FHIR regulations, the action itself is non-destructive and produces no side effects. The blast radius if misused would be unauthorized disclosure of patient medication data, but not data loss, modification, or financial impact.
From the tool's definition Tool name 'get_patient_medications' and description 'Get patient's medications' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get patient's medications. It is categorised as a Read tool in the FHIR Careplan MCP Server, which means it retrieves data without modifying state.
Register the FHIR Careplan MCP server in PolicyLayer and add a rule for get_patient_medications: 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 FHIR Careplan. Nothing to install.
get_patient_medications 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_medications 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_medications. 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_medications is provided by the FHIR Careplan MCP server (kushagra-dutta/fhir-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 →