AI agents call search_medical_concept to retrieve information from Medterms without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the NIH UMLS Metathesaurus to retrieve medical terminology definitions and identifiers. It has no side effects, cannot modify data, execute code, delete records, or move money. The search operation is read-only and returns structured medical reference data. Even in adversarial use, misuse would only produce incorrect or misleading lookups, not system compromise or data damage.
From the tool's definition Tool description states it 'Search for a medical concept' and 'Returns concept definitions and cross-system identifiers' — pure information retrieval with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search for a medical concept across terminology systems (SNOMED CT, MeSH, LOINC, NCI Thesaurus) using the NIH UMLS Metathesaurus. Returns concept definitions and cross-system identifiers. It is categorised as a Read tool in the Medterms MCP Server, which means it retrieves data without modifying state.
Register the Medterms MCP server in PolicyLayer and add a rule for search_medical_concept: 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 Medterms. Nothing to install.
search_medical_concept 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_medical_concept 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_medical_concept. 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_medical_concept is provided by the Medterms MCP server (pubspro/medterms-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 →