Search clinical trials by study acronym. Uses the Acronym field (protocolSection.identificationModule.acronym) to find trials by their public short name. Example: 'TETON'. The API search is seeded with the provided acronyms to narrow results, then results are filtered locally to ensure the acron...
Part of the Clinical Trials Data Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call search_trials_by_acronym 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 search_trials_by_acronym 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.
tools:
search_trials_by_acronym:
rules:
- action: allowSee the full Clinical Trials Data Server policy for all 12 tools.
Agents calling read-class tools like search_trials_by_acronym have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Search clinical trials by study acronym. Uses the Acronym field (protocolSection.identificationModule.acronym) to find trials by their public short name. Example: 'TETON'. The API search is seeded with the provided acronyms to narrow results, then results are filtered locally to ensure the acronym field matches the requested value(s). Input: - `acronyms`: One or more acronyms to search for (e.g., ['TETON']). - `max_studies`: Maximum number of studies to request from the API. - `exact_match`: When true (default), matches acronyms exactly (case-insensitive). When false, matches if any provided acronym is contained within the study acronym (case-insensitive partial match). - `fields`: A list of specific fields to return in the results. If not provided, returns ACRONYM_SEARCH_DEFAULTS (8 fields optimized for acronym discovery: NCTId, BriefTitle, Acronym, Condition, InterventionName, Phase, LeadSponsorName, HasResults).. It is categorised as a Read tool in the Clinical Trials Data Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for search_trials_by_acronym. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Clinical Trials Data Server MCP server.
search_trials_by_acronym 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 search_trials_by_acronym rule in your Intercept 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 Intercept policy for search_trials_by_acronym. 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.
search_trials_by_acronym is provided by the Clinical Trials Data Server MCP server (plainyogurt21/clintrials-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept