AI agents call fhir_search to retrieve information from Healow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only retrieval of FHIR clinical data. While it accesses sensitive patient health information (PHI), which warrants medium severity due to privacy implications, the tool itself has no side effects—it does not create, modify, delete, or execute operations. The 'arbitrary query params' phrasing suggests flexibility in search criteria, but the core function remains data retrieval.
From the tool's definition Tool name 'fhir_search' and description 'Search any FHIR resource type with arbitrary query params. Returns the raw' indicate a query/search operation that retrieves data without modification.
Attacks that exploit this kind of access
Search any FHIR resource type with arbitrary query params. Returns the raw. It is categorised as a Read tool in the Healow MCP Server, which means it retrieves data without modifying state.
Register the Healow MCP server in PolicyLayer and add a rule for fhir_search: 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 Healow. Nothing to install.
fhir_search 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 fhir_search 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 fhir_search. 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.
fhir_search is provided by the Healow MCP server (voysi-ia/healow-mcp-server). 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 →