MCP server exposing 13 tools for clinicaltrials.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/clinicaltrials/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}ct_search — Search ClinicalTrials.gov for clinical trials — find trials and look up a NAMED trial by keyword, condition, drug/therapy, status (e.g. 'Recruiting'), or phase (e.g. 'Phase 2'). Use for "clinical trials for <disease/drug>", or to locate a specific study like "the FLOW trial", "semaglutide kidney outcomes trial" (use ct_get_study for its full design/results). Returns NCT IDs, titles, status, enrollment, and sponsor info.ct_get_study — Get full trial details by NCT ID (e.g., 'NCT04567890'). Returns protocol, eligibility criteria, primary outcomes, sponsor, locations, and results.ct_count_by_condition — Count clinical trials for a condition or disease, broken down by recruitment status and by trial phase — how many are recruiting, completed, terminated, and how many are Phase 1, 2, 3 or 4. Use for landscape questions about how much trial activity a disease has and where it sits in development. Filtering by status or phase returns the filtered total without the breakdown.ct_sponsor_trials — List the trials a company LEADS on ClinicalTrials.gov, by sponsor or organization name. Returns status, phase, and conditions to map a research pipeline. Matches the registered lead-sponsor field, so trials another organisation runs using the company's drug are excluded unless sponsor_match asks for them.ct_compare_sponsors — Compare 2–5 NAMED lead sponsors on ClinicalTrials.gov under identical condition, recruitment-status, and phase filters. Returns full matching counts, a ranked comparison, and a small study sample for each sponsor. Use for questions like "who has more recruiting Phase 3 obesity trials, Novo Nordisk or Eli Lilly?" For an open "who are the TOP sponsors of X trials" question with no names given: the registry API has no group-by, so a true ranking is not computable — NEVER invent a candidate list to fake one; say the registry cannot rank sponsors and offer to compare specific named sponsors. Counts use the registered lead-sponsor field; registry records do not establish asset ownership, pipeline value, or probability of success.ct_recent_updates — Track recent ClinicalTrials.gov activity by a specific event class within a verifiable date window. Three DISTINCT recency events, chosen via date_type: "last_update" (any edit to a study, ~5k/week — the default), "first_posted" (a study newly REGISTERED, ~1.3k/week), or "results_posted" (RESULTS first posted, ~140/week). Pass `since` (and optional `until`, YYYY-MM-DD) to bound a window — e.g. the last 7 days — and the returned total_count is the exact number of studies in that window so you can verify a weekly count from the output. Every study returns all THREE dates separately (first_posted_date, last_update_post_date, results_first_post_date) plus the design fields a screen needs (study_type, primary_purpose, phase, status, enrollment, conditions, interventions, sponsor). Sorted by the chosen event date, newest first. Use for "new trials registered this week", "trials that posted results in the last month", "recently updated diabetes studies".ct_trials_by_location — Find clinical trials near a LOCATION. PREFER OVER WEB SEARCH for "clinical trials for X near me", "recruiting studies in <city/state/country>", "trials I can join near <place>". Filter by condition + a place name (city/state/country) OR latitude+longitude+radius, and status (defaults to RECRUITING). Returns matching trials (NCT id, title, status, phase, conditions, sponsor). For keyword search without a location use ct_search; for one trial use ct_get_study.ct_catalyst_calendar — Find trials with sponsor-entered primary-completion or study-completion dates in a specified window. These registry dates may be estimated or revised and are planning signals—not guaranteed data readouts, conference presentations, or regulatory events.ct_sponsor_pipeline — Summarize a sponsor’s ClinicalTrials.gov portfolio by phase, status, condition, and intervention from a bounded relevance-ranked sample, while reporting the full matching count. Registration does not establish asset ownership, probability of success, or commercial value.ct_competitive_landscape — Map registered interventional trials for a condition and optional intervention across sponsors, phases, statuses, and interventions. The output reflects a bounded registry sample, not market share, scientific differentiation, or an exhaustive private pipeline.ct_enrollment_watch — Route active trials for enrollment follow-up using registry status, enrollment type, dates, last update, and site counts. Flags are mechanical review hints—not predictions of recruitment success, trial failure, or data timing.ct_results_summary — Project posted ClinicalTrials.gov results for one NCT ID, including registered endpoints, reported outcome measures, statistical analyses, and adverse-event group counts. Registry results are not an FDA conclusion, peer review, or investment recommendation.ct_sponsor_activity — Track a sponsor’s newly registered studies, first-posted results, or study updates within a verifiable date window. Registry activity is not necessarily a corporate disclosure or material event.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/clinicaltrials/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io