Full ClinicalTrials.gov study record by NCT id — the deep detail beyond clinical.trial-search. Returns description, status, phases, conditions, design (allocation/model/purpose/masking), enrollment, interventions, primary + secondary outcome measures (with time frames), full eligibility criteria ...
AI agents call clinical.study-detail 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 performs read-only queries against publicly available clinical trial data. It has no side effects, does not modify data, execute code, delete records, or commit financial obligations. The retrieval of structured metadata about clinical studies poses minimal risk even if misused by an AI agent.
From the tool's definition Tool retrieves clinical trial details from ClinicalTrials.gov by NCT id. Description explicitly states it 'Returns description, status, phases, conditions, design, enrollment, interventions, outcome measures, eligibility criteria, lead sponsor, facility…
Attacks that exploit this kind of access
Full ClinicalTrials.gov study record by NCT id — the deep detail beyond clinical.trial-search. Returns description, status, phases, conditions, design (allocation/model/purpose/masking), enrollment, interventions, primary + secondary outcome measures (with time frames), full eligibility criteria (text, sex, age range, healthy-volunteers), lead sponsor + collaborators, all facility locations, results-posted flag, and key dates. Free, public-domain (NIH NLM). Find an NCT id with clinical.trial-search, then use this. 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.study-detail: 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.study-detail 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.study-detail 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.study-detail. 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.study-detail 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 →