ClinicalTrials.gov Search Scraper

Search clinical trials by condition, drug, sponsor, location, status or phase and export clean, flat study records.

Get structured clinical trial data from ClinicalTrials.gov as JSON, CSV or Excel, or call it as a tool from Claude, Cursor, ChatGPT or any MCP client. Built on the official ClinicalTrials.gov API v2, so it does not break when the website changes. Pay only for the studies you receive.

What you get

One record per study with the fields people actually filter on: NCT ID and link, titles, status and why stopped, study type, phases, conditions and keywords, interventions with type, lead sponsor and class, collaborators, enrollment count and type, design (allocation, model, purpose, masking), eligibility (sex, age range, healthy volunteers), primary outcomes, all key dates (start, primary completion, completion, first posted, last updated), whether results are posted, countries, site count and up to 50 site locations, plus the brief summary and eligibility criteria text.

Every result is a flat record with stable field names, so it drops straight into a spreadsheet, a database or an AI agent's context.

Why use this instead of the website

• Combine condition, intervention, sponsor, location, status, phase, study type and date filters in one call
• Pagination handled for you, with automatic retries and polite rate limiting
• Results in JSON, CSV, Excel or via API, or piped into Zapier, Make, n8n and Google Sheets
• Works as an MCP tool, so AI agents can look up trials on demand
• No browser, no proxies, no personal data: fast runs and a tiny cost per result
• Monitoring made easy: set "Updated after" to yesterday and schedule the Actor daily to catch new and changed trials

Input

Field	Type	Default	Meaning
condition	string		Condition or disease, e.g. "type 2 diabetes"
query	string		Free-text terms searched across the whole record
intervention	string		Drug, device or procedure name
sponsor	string		Sponsor or collaborator organization
location	string		City, state, country or facility
status	array	all	Any of RECRUITING, NOT_YET_RECRUITING, ENROLLING_BY_INVITATION, ACTIVE_NOT_RECRUITING, COMPLETED, SUSPENDED, TERMINATED, WITHDRAWN, UNKNOWN
phase	array	all	Any of EARLY_PHASE1, PHASE1, PHASE2, PHASE3, PHASE4, NA
studyType	string	any	INTERVENTIONAL, OBSERVATIONAL or EXPANDED_ACCESS
updatedAfter	date		Only records updated on or after YYYY-MM-DD
startedAfter	date		Only studies starting on or after YYYY-MM-DD
nctIds	array		Specific NCT numbers to fetch
sort	string	last updated	Last updated, first posted, start date, enrollment or relevance
includeLocations	boolean	true	Include up to 50 site locations per study
includeSummary	boolean	true	Include brief summary and eligibility criteria text
maxResults	integer	100	Cap on studies saved. You are charged per study, so this caps your cost.

Example input:

{
  "condition": "type 2 diabetes",
  "intervention": "semaglutide",
  "status": ["RECRUITING", "NOT_YET_RECRUITING"],
  "phase": ["PHASE3"],
  "location": "United States",
  "maxResults": 200
}

Output

Example result (shortened):

{
  "nctId": "NCT05000000",
  "url": "https://clinicaltrials.gov/study/NCT05000000",
  "briefTitle": "Semaglutide in Adults With Type 2 Diabetes and Obesity",
  "overallStatus": "RECRUITING",
  "studyType": "INTERVENTIONAL",
  "phases": ["PHASE3"],
  "conditions": ["Type 2 Diabetes", "Obesity"],
  "interventions": [{ "type": "DRUG", "name": "Semaglutide" }, { "type": "DRUG", "name": "Placebo" }],
  "leadSponsor": "Example Pharma A/S",
  "leadSponsorClass": "INDUSTRY",
  "enrollmentCount": 1200,
  "enrollmentType": "ESTIMATED",
  "allocation": "RANDOMIZED",
  "masking": "QUADRUPLE",
  "sex": "ALL",
  "minimumAge": "18 Years",
  "primaryOutcomes": ["Change in HbA1c from baseline to week 52"],
  "startDate": "2025-03-01",
  "primaryCompletionDate": "2027-06-30",
  "lastUpdatePostedDate": "2026-09-10",
  "hasResults": false,
  "locationsCount": 84,
  "countries": ["United States", "Canada", "Germany"],
  "locations": [{ "facility": "Example Research Center", "city": "Phoenix", "state": "Arizona", "country": "United States", "status": "RECRUITING" }],
  "briefSummary": "This study compares ..."
}

Field reference: nctId, url, briefTitle, officialTitle, overallStatus, whyStopped, studyType, phases[], conditions[], keywords[], interventions[]{type,name}, leadSponsor, leadSponsorClass, collaborators[], enrollmentCount, enrollmentType, allocation, interventionModel, primaryPurpose, masking, sex, minimumAge, maximumAge, healthyVolunteers, primaryOutcomes[], startDate, primaryCompletionDate, completionDate, firstPostedDate, lastUpdatePostedDate, hasResults, locationsCount, countries[], locations[]{facility,city,state,country,status}, briefSummary, eligibilityCriteria. Dates are strings as published (YYYY-MM-DD or YYYY-MM).

Pricing

Pay per event. You are charged $2.00 per 1,000 studies saved to the dataset, plus a fraction of a cent per run start. Nothing is charged for results you do not receive. Set "Max total charge per run" in the run options to cap spending on any run. When a run reaches your cap it stops cleanly and keeps everything it already saved.

Rough guide: 1,000 studies cost $2.00 and take about 25 seconds.

Use it from an AI agent (MCP)

This Actor is available as an MCP tool through the Apify MCP server. Add it to your client, then ask the agent for the data in plain language.

Claude Desktop, Claude Code or Cursor (mcp.json / claude_desktop_config.json):

{
  "mcpServers": {
    "apify": {
      "url": "https://mcp.apify.com/?actors=brightpath-data/clinicaltrials-gov-search",
      "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }
    }
  }
}

ChatGPT and other clients that support remote MCP servers: add https://mcp.apify.com/?actors=brightpath-data/clinicaltrials-gov-search as a connector with your Apify token.

Example prompt once connected: "Find recruiting phase 3 trials for type 2 diabetes in Arizona and list the sponsor, enrollment and primary outcome for each."

Use it from code

curl -X POST "https://api.apify.com/v2/acts/brightpath-data~clinicaltrials-gov-search/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"condition":"type 2 diabetes","status":["RECRUITING"],"maxResults":100}'

Python:

from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("brightpath-data/clinicaltrials-gov-search").call(run_input={"condition": "type 2 diabetes", "status": ["RECRUITING"], "maxResults": 100})
items = client.dataset(run["defaultDatasetId"]).list_items().items

Limits and fair use

• Up to 10,000 studies per run. For larger exports, split by status, phase, date range or country.
• Requests are paced at one per second to respect the source's crawl delay, so very large runs take a few minutes.
• Site locations are capped at 50 per study; locationsCount always shows the full number.
• Study contacts and investigator names are intentionally not collected.

Data source and legal

Data comes from ClinicalTrials.gov, a public registry run by the U.S. National Library of Medicine, through its official public API v2. The data is in the public domain. This Actor collects public, non-personal data only and does not bypass logins, paywalls or access controls. You are responsible for how you use the data.

Support

Found a problem or need a field added? Open an issue on the Actor's Issues tab. Fixes for broken runs are prioritized.