AI agents call terminology.expand 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.
The terminology.expand tool retrieves and enumerates codes contained within a FHIR ValueSet. This is a non-destructive query operation with no side effects—it does not create, modify, delete, or execute code. While it accesses healthcare terminology data (which is PHI-adjacent), the operation itself is a safe read. The server's PHI protection and audit logging further mitigate risks at the infrastructure level.
From the tool's definition Tool name 'expand' and description 'Expand a ValueSet to get contained codes' indicate data retrieval operation. ValueSet expansion is a standard FHIR read operation that returns codes without modifying data.
Attacks that exploit this kind of access
Expand a ValueSet to get contained codes. 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.expand: 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.expand 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.expand 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.expand. 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.expand 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 →