Search for patients in the FHIR server
AI agents call search_patients to retrieve information from FHIR MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries patient data from a healthcare system without modifying, deleting, or executing operations. It falls clearly under the Read category. Severity is high rather than medium because: (1) it accesses protected health information (PHI) regulated under HIPAA and similar frameworks; (2) an AI agent with unrestricted access could retrieve large volumes of sensitive patient data; (3) the blast…
From the tool's definition Tool name is 'search_patients' and description states 'Search for patients in the FHIR server'. The verb 'search' indicates a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
Search for patients in the FHIR server. It is categorised as a Read tool in the FHIR MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FHIR MCP Server MCP server in PolicyLayer and add a rule for search_patients: 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 MCP Server. Nothing to install.
search_patients 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 search_patients 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 search_patients. 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.
search_patients is provided by the FHIR MCP Server MCP server (jcafazzo/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 →