Loading ToolBench
ClinicalTrials.gov Model Context Protocol (MCP) Server that provides a suite of tools for interacting with the official ClinicalTrials.gov v2 API. Enables AI agents and LLMs to programmatically search, retrieve, compare, analyze, and find eligible clinical trials.
Strong tool definitions with clear naming, comprehensive parameter schemas, and good descriptions. All 5 tools follow verb_noun convention (clinicaltrials_*). Schemas are well-structured with type constraints, enums, and ranges. Descriptions average ~150 chars, meeting the 10-1024 baseline. However, output schemas are not documented in the provided source, and error handling guidance is absent. Tool composition is sound, each tool has a single responsibility and clear use case. Parameter descriptions are detailed and include constraints (e.g., age 0-120, maxResults 1-50). No security issues detected (read-only operations, no credential parameters).
Performs statistical analysis on clinical trial studies matching search criteria. Aggregates data by status, country, sponsor type, phase, year, or month. May fetch up to 5000 studies.
Performs side-by-side comparison of 2-5 clinical trial studies. Compares eligibility criteria, design, interventions, outcomes, sponsors, and other key aspects.
Matches patient demographics and medical profile to eligible clinical trials. Filters by age, sex, conditions, location, and healthy volunteer status. Returns ranked list of matching studies with eligibility explanations.
Fetches one or more clinical trial studies from ClinicalTrials.gov by their NCT ID(s). Returns full study data or concise summaries.
Searches for clinical trial studies from ClinicalTrials.gov using queries and filters. Supports pagination, sorting, and advanced filtering.
Output schemas not documented. Tool descriptions state what is returned (e.g., 'Returns full study data or concise summaries') but do not specify field names, types, or structure. LLMs cannot plan downstream operations without knowing response shape.
No error handling guidance. Tools lack descriptions of failure modes, recovery steps, or actionable error messages. E.g., what happens if an NCT ID is invalid? What should the agent do?
Pagination not fully specified. clinicaltrials_search_studies accepts pageToken but does not document how to detect end-of-results or what pageToken format is. Missing total count or next_cursor guidance.
Inferred effective spec: 2026-07-28+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 68 | 2026-07-28+ | v2 |
Parameter 'filter' in clinicaltrials_analyze_trends and clinicaltrials_search_studies references 'ClinicalTrials.gov filter syntax' but does not provide examples or link to documentation. LLMs cannot construct valid filters without concrete guidance.
clinicaltrials_find_eligible_studies location parameter is an object with optional nested fields (country, state, city, postalCode) but does not specify which combinations are valid or required. Can an agent pass only city without country?