AI agents call lookup_meddra 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 retrieves standardized medical terminology metadata from a reference database. It has no side effects, does not modify data, and does not execute external operations or financial transactions. The stated use cases (adverse event coding, pharmacovigilance, regulatory submissions) all involve reading pre-existing standardized classifications.
From the tool's definition Tool is described as a lookup function that identifies and retrieves hierarchical information about MedDRA terms (PT, SOC, related terms). The verb 'look up' and 'identify' indicate data retrieval with no modification capability.
Attacks that exploit this kind of access
Look up a MedDRA Preferred Term (PT), identify its System Organ Class (SOC), hierarchy level, and related terms. Critical for adverse event coding, pharmacovigilance, and regulatory submissions. 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 lookup_meddra: 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.
lookup_meddra 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 lookup_meddra 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 lookup_meddra. 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.
lookup_meddra 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 →