AI agents call get_trial_details to retrieve information from Pgx 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 clinical trial information from public databases (likely ClinicalTrials.gov via NCT ID lookup). It has no side effects, does not execute code or commands, does not modify data, and does not involve financial transactions. The blast radius of misuse is minimal—an agent might retrieve irrelevant or sensitive trial information, but cannot alter, delete, or execute external operations.
From the tool's definition Tool name 'get_trial_details' and description 'Get full details for a specific clinical trial by NCT ID' indicate a retrieval operation.
Attacks that exploit this kind of access
Get full details for a specific clinical trial by NCT ID. It is categorised as a Read tool in the Pgx MCP Server, which means it retrieves data without modifying state.
Register the Pgx MCP server in PolicyLayer and add a rule for get_trial_details: 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 Pgx. Nothing to install.
get_trial_details 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 get_trial_details 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 get_trial_details. 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.
get_trial_details is provided by the Pgx MCP server (julius-schmidt/mcp-pharmacogenomics). 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 →