Read one patient's demographics. reason is recorded in the audit trail.
AI agents call get_patient to retrieve information from Fhir Synthetic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves patient demographic data without modification, deletion, or execution of external operations. It is a straightforward query operation with audit logging. The presence of audit trails and the gated write workflow on the server reinforces that this is a read-only operation.
From the tool's definition Tool name is 'get_patient' and description states 'Read one patient's demographics' with no side effects mentioned. Reason is logged for audit purposes only.
Attacks that exploit this kind of access
Read one patient's demographics. reason is recorded in the audit trail. It is categorised as a Read tool in the Fhir Synthetic MCP Server, which means it retrieves data without modifying state.
Register the Fhir Synthetic MCP server in PolicyLayer and add a rule for get_patient: 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 Synthetic. Nothing to install.
get_patient 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 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. 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 is provided by the Fhir Synthetic MCP server (krishnakakani-github/fhir-synthetic-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 →