AI agents call terminology.lookup to retrieve information from FhirMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries terminology data to retrieve code properties and display information without modifying anything. However, severity is rated high because it operates on healthcare FHIR terminology systems that may contain clinically significant information. The blast radius is elevated due to the healthcare context and potential for information disclosure, even though the operation itself is read-only.
From the tool's definition Tool description states 'Look up properties and display for a code' which performs data retrieval only. No create/update/delete language present. The verb 'look up' and 'display' indicate read-only query operations.
Attacks that exploit this kind of access
Look up properties and display for a code in a CodeSystem. It is categorised as a Read tool in the FhirMCP MCP Server, which means it retrieves data without modifying state.
Register the Fhir MCP server in PolicyLayer and add a rule for terminology.lookup: 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 FhirMCP. Nothing to install.
terminology.lookup 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 terminology.lookup 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 terminology.lookup. 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.
terminology.lookup is provided by the Fhir MCP server (xsovx/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 →