ClinicalTrials.gov Studies Feed — Trials API

Structured, deduplicated clinical-trial records pulled directly from ClinicalTrials.gov, the official U.S. National Library of Medicine registry of clinical studies. Instead of parsing the registry's deeply nested API response yourself, you get one clean, flat schema — title, phase, sponsor, enrollment, key dates, locations, and eligibility — ready to export, pipe into a database, or query from an AI agent.

Run it with zero configuration to get currently recruiting cancer trials, or filter by condition, free-text term, sponsor, recruitment status, or phase.

What it does

ClinicalTrials.gov publishes structured study data through its official data API v2 (https://clinicaltrials.gov/api/v2/studies). The raw response is powerful but verbose: every study is a deeply nested protocolSection object with a dozen sub-modules, and pagination is cursor-based (you have to follow a nextPageToken, not a page number).

This actor handles all of that. It queries the API with your filters, follows the cursor across pages, maps each study from its nested JSON into one flat record, deduplicates on nctId, sorts by most recently updated, and writes the result to your dataset — ready to export as JSON, CSV, or Excel, feed into a webhook, or read from an AI assistant over MCP.

No API key. No scraping. ClinicalTrials.gov data is U.S. government public-domain content, free for commercial use.

Why a clean trials feed matters

Professional clinical-trial intelligence platforms (Cortellis, Citeline, AdisInsight) cost tens of thousands of dollars a year. A huge long tail of users needs the same underlying registry data but can't justify that spend:

• Biotech & pharma analysts — track competitors' pipelines: who is running which phase, in which indication, with how many patients, and when readouts are due.
• VC & investment associates — diligence a company's clinical assets, map a therapeutic area's competitive landscape, and monitor status changes before they hit the news.
• Competitive-intelligence teams — watch a named sponsor's active and completed trials and get a structured feed instead of manually re-searching the registry.
• Academics & systematic reviewers — pull every recruiting trial for a condition into a spreadsheet for screening, without hand-copying from the website.
• Patient-recruitment & site teams — find recruiting trials by condition and location to match patients or benchmark enrollment.
• Data & AI builders — feed normalized trial records into a RAG pipeline, dashboard, or alerting system.

Input

Every field is optional. Empty input {} returns currently recruiting cancer trials.

Field	Type	Default	Description
condition	string	cancer	Condition / disease to search (CT.gov query.cond). Example: breast cancer, type 2 diabetes. Defaults to cancer when no condition, term, or sponsor is given.
term	string	—	Free-text search across the whole record (CT.gov query.term). Example: immunotherapy, CAR-T, semaglutide.
sponsor	string	—	Lead-sponsor / collaborator filter (CT.gov query.spons). Example: Pfizer, National Cancer Institute.
overallStatus	array	["RECRUITING"]	Recruitment statuses to include. Valid values: RECRUITING, NOT_YET_RECRUITING, ACTIVE_NOT_RECRUITING, ENROLLING_BY_INVITATION, COMPLETED, SUSPENDED, TERMINATED, WITHDRAWN, and more.
phase	string	"" (any)	Single trial phase: EARLY_PHASE1, PHASE1, PHASE2, PHASE3, PHASE4, NA.
maxStudies	integer	200	Cap on total records output after dedupe. Large pulls are cursor-paginated and throttled to respect the public API.

Zero-config (recruiting cancer trials)

{}

By condition + phase

{
  "condition": "type 2 diabetes",
  "phase": "PHASE3",
  "overallStatus": ["RECRUITING"],
  "maxStudies": 100
}

By sponsor (full pipeline, any status)

{
  "sponsor": "Moderna",
  "overallStatus": ["RECRUITING", "ACTIVE_NOT_RECRUITING", "COMPLETED"],
  "maxStudies": 500
}

Output

One item per study, deduplicated on nctId, sorted by most recently updated. Missing values are null — never fabricated.

Field	Type	Description
nctId	string	ClinicalTrials.gov identifier, e.g. NCT06649227.
briefTitle	string	Short study title.
officialTitle	string	Full official title.
overallStatus	string	Recruitment status, e.g. RECRUITING.
phase	string	Trial phase(s), |-joined for multi-phase, e.g. PHASE2|PHASE3.
studyType	string	INTERVENTIONAL, OBSERVATIONAL, etc.
conditions	array	Conditions / diseases studied.
interventions	array	Interventions as TYPE: name, e.g. DRUG: pembrolizumab.
sponsorName	string	Lead sponsor name.
sponsorClass	string	Sponsor class, e.g. INDUSTRY, NIH, OTHER.
enrollmentCount	integer	Target / actual enrollment.
startDate	string	Study start date (YYYY-MM-DD or YYYY-MM).
primaryCompletionDate	string	Primary completion date.
completionDate	string	Overall completion date.
locations	array	Sites as {facility, city, country}.
eligibilityCriteria	string	Brief inclusion/exclusion excerpt (truncated).
lastUpdatePostDate	string	Date the record was last updated on CT.gov.
studyUrl	string	https://clinicaltrials.gov/study/{nctId}.

Sample item

{
  "nctId": "NCT06649227",
  "briefTitle": "Study Investigating the Safety of CD19 CAR-T Cells in Relapsed/Refractory AML",
  "overallStatus": "RECRUITING",
  "phase": "PHASE1",
  "studyType": "INTERVENTIONAL",
  "conditions": ["Relapsed Adult AML"],
  "interventions": ["DRUG: CAR-T cell therapy"],
  "sponsorName": "University Hospital, Lille",
  "sponsorClass": "OTHER",
  "enrollmentCount": 5,
  "startDate": "2025-07-10",
  "primaryCompletionDate": "2029-07-10",
  "completionDate": "2030-07-10",
  "locations": [{ "facility": "CHU de Lille", "city": "Lille", "country": "France" }],
  "lastUpdatePostDate": "2025-12-05",
  "studyUrl": "https://clinicaltrials.gov/study/NCT06649227"
}

Use cases

• Pipeline tracking — schedule a daily run on a sponsor or indication and diff the output to catch new trials and status changes.
• Competitive landscape — pull every Phase 2/3 trial for a target into a slide-ready table.
• Research datasets — build a screening spreadsheet for a systematic review in one run.
• AI agents — connect over MCP so an assistant can answer "what Phase 3 diabetes trials are recruiting?" with live registry data.

Source

All data comes from the official ClinicalTrials.gov data API v2, published by the U.S. National Library of Medicine (NIH). It is public-domain U.S. government data. This actor only reads and reshapes that public data — it adds no editorial content.

What this actor is NOT

• Not medical advice. This is registry metadata for research and intelligence use, not guidance for treatment, enrollment, or any clinical decision. Always consult the official study record and a qualified professional.
• Not a private or enriched dataset. It mirrors what ClinicalTrials.gov already publishes. It does not add analysis, predictions, or data not present in the source record.
• Not real-time push. Each run is a point-in-time snapshot; schedule runs for monitoring. Records reflect CT.gov's own lastUpdatePostDate, which can lag sponsor activity.
• Not affiliated with ClinicalTrials.gov, the NIH, or the U.S. National Library of Medicine.