AI agents call clinical.trial-search to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries publicly available clinical trial data with no side effects. It is a straightforward read operation that returns information without altering any state or triggering actions beyond the search itself. The low severity reflects minimal blast radius—misuse would only result in inappropriate search results, not data loss or unauthorized actions.
From the tool's definition Tool performs a search operation on ClinicalTrials.gov with 'free-text query' and optional filters for 'recruitment status, sponsor, phase, country'. No modification, deletion, or execution of external operations is described.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Search ClinicalTrials.gov — every registered US (+ many international) clinical study (~500k). Free-text query, or direct NCT ID. Optional filters: recruitment status, sponsor, phase, country. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for clinical.trial-search: 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 Mcp. Nothing to install.
clinical.trial-search 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 clinical.trial-search 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 clinical.trial-search. 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.
clinical.trial-search is provided by the MCP server (@2sio/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 →