AI agents call lookup_ctcae 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 performs a simple lookup/query operation against a medical reference database (CTCAE standards). It retrieves existing safety grading criteria without creating, modifying, executing, deleting, or moving any data or financial resources. The operation is read-only and informational, supporting clinicians and researchers in standardized adverse event assessment.
From the tool's definition Tool description indicates 'Look up' functionality for CTCAE grading criteria—a retrieval operation with no modification, execution, or deletion capabilities. CTCAE is a reference standard used to grade severity of adverse events in clinical trials.
Attacks that exploit this kind of access
Look up NCI Common Terminology Criteria for Adverse Events (CTCAE) grading criteria for an adverse event. Essential for oncology clinical trial safety reporting. 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_ctcae: 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_ctcae 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_ctcae 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_ctcae. 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_ctcae 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 →