Retrieve detailed clinical trial records in batches to reduce payload during discovery. Accepts a list of NCT IDs and fetches details in batches (default 10). Preserves the order of input NCT IDs in the returned list. Use this after search tools which return a minimal field set. Input: - nct_ids:...
Part of the Clinical Trials Data Server server.
Free to start. No card required.
AI agents call get_trial_details_batched to retrieve information from Clinical Trials Data Server without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_trial_details_batched only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_trial_details_batched": {}
}
}See the full Clinical Trials Data Server policy for all 12 tools.
These attack patterns abuse exactly the kind of access get_trial_details_batched gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Retrieve detailed clinical trial records in batches to reduce payload during discovery. Accepts a list of NCT IDs and fetches details in batches (default 10). Preserves the order of input NCT IDs in the returned list. Use this after search tools which return a minimal field set. Input: - nct_ids: List of NCT IDs to retrieve in batches. - fields: Specific fields to return. If not provided, returns DETAIL_TOOL_DEFAULTS (25 comprehensive fields covering: NCTId, BriefTitle, OfficialTitle, Acronym, Condition, Keyword, Phase, OverallStatus, InterventionType, InterventionName, InterventionDescription, ArmGroupLabel, ArmGroupType, ArmGroupDescription, EligibilityCriteria, MinimumAge, MaximumAge, Sex, PrimaryOutcomeMeasure, SecondaryOutcomeMeasure, BriefSummary, LocationFacility, LocationCountry, LeadSponsorName, CollaboratorName, HasResults). - batch_size: Number of trials to fetch per API call (default 10).. It is categorised as a Read tool in the Clinical Trials Data Server MCP Server, which means it retrieves data without modifying state.
Register the Clinical Trials Data Server MCP server in PolicyLayer and add a rule for get_trial_details_batched: 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 Clinical Trials Data Server. Nothing to install.
get_trial_details_batched 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_batched 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_batched. 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_batched is provided by the Clinical Trials Data Server MCP server (plainyogurt21/clintrials-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 Clinical Trials Data Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.