ClinicalTrials.gov Monitor — New Trials by Condition & Sponsor

Track newly posted ClinicalTrials.gov studies by condition, keyword, sponsor and recruitment status. NCT ID, titles, phase, status, sponsor and dates as clean JSON from the official ClinicalTrials.gov API — with NCT-ID memory so a scheduled run flags exactly what is new.

What does this Actor do?

You give it conditions, keywords, a sponsor and a set of recruitment statuses. It queries the official ClinicalTrials.gov API once per condition and once per keyword, merges the results by NCT ID, keeps only studies whose first-posted date falls in the window, sorts them newest-first, and emits them.

Two details make it a monitor rather than a search. First, the window is anchored on studyFirstPostDateStruct — the date the study first appeared on the registry — not on the study's start date or last-update date, which is what you actually want when the question is "what is new?". Second, it keeps a list of NCT IDs it has already seen across runs, so newSinceLastRun tells you truthfully whether a study is genuinely new to you or was in a previous run's window.

Who is it for?

• Competitive intelligence teams at pharma and biotech watching what rivals put into the clinic.
• CRO business development looking for newly posted studies that need sites or services.
• Patient-recruitment agencies tracking recruiting studies by condition and geography.
• Biotech investors and analysts monitoring a sponsor's pipeline as it becomes public.
• Medical journalists and researchers following trial activity in a therapeutic area.
• AI agent builders who want a clinical-trials tool with a stable output schema.

Use cases

• Watch one condition — melanoma, ALS, type 2 diabetes — for every newly posted study.
• Monitor a named sponsor's registrations as an early read on their pipeline.
• Track only RECRUITING studies in your therapeutic area for site-selection outreach.
• Feed new Phase 3 registrations into a competitive-intelligence digest.
• Give an agent a tool that answers "what trials were just posted for this condition?"

What you get

One row per study. Any value the source does not publish is null — the field is always present, and the untouched protocol section stays in raw.

Field	Type	Description
nctId	string	ClinicalTrials.gov identifier, e.g. NCT06712345 — the unique key the seen-list tracks
briefTitle	string	Short study title
officialTitle	string	Full official study title
overallStatus	string	Recruitment status, e.g. RECRUITING, NOT_YET_RECRUITING, COMPLETED
conditions	array	Conditions the study addresses
phases	array	Trial phases, e.g. ["PHASE2", "PHASE3"]
locations	array	Up to 25 convenient location extracts (facility, city, state, country, status); complete source locations remain in raw
centralContacts	array	Up to 5 central-contact extracts, with published name, role, phone and email fields
leadSponsor	string	Lead sponsor name
organization	string	Sponsoring organization's full name
firstPostedDate	string	Date the study first appeared on ClinicalTrials.gov
startDate	string	Study start date, where published
briefSummary	string	Study summary, truncated to 500 characters
url	string	Direct link to the study on clinicaltrials.gov
raw	object	The complete original protocol section, unmodified
newSinceLastRun	boolean	true if this NCT ID had not been seen on an earlier successful run
retrievedAt	string	ISO 8601 timestamp of when this row was fetched

Sample output record

{
  "nctId": "NCT06712345",
  "briefTitle": "Study of Compound X in Advanced Melanoma",
  "officialTitle": "A Phase 2, Open-Label Study of Compound X in Participants With Unresectable or Metastatic Melanoma",
  "overallStatus": "RECRUITING",
  "conditions": ["Melanoma", "Skin Neoplasms"],
  "phases": ["PHASE2"],
  "leadSponsor": "Example Therapeutics, Inc.",
  "organization": "Example Therapeutics, Inc.",
  "firstPostedDate": "2026-08-19",
  "startDate": "2026-09-01",
  "briefSummary": "This study evaluates the safety and efficacy of Compound X in participants with…",
  "url": "https://clinicaltrials.gov/study/NCT06712345",
  "raw": { "identificationModule": { "…": "…" } },
  "newSinceLastRun": true,
  "retrievedAt": "2026-08-23T09:52:18.663Z"
}

How to use it

Watch a condition for recruiting studies

{
  "conditions": ["melanoma"],
  "statuses": ["RECRUITING"],
  "maxResults": 25
}

Follow a sponsor's pipeline

sponsor is applied to every query rather than being a query of its own.

{
  "conditions": ["oncology"],
  "sponsor": "Example Therapeutics",
  "maxResults": 100
}

Everything newly posted

Leave conditions and keywords empty to track all newly posted studies.

{
  "postedSince": "2026-08-01",
  "maxResults": 500
}

Input parameters

Input	Type	Description
conditions	array	Conditions, each queried separately. Empty with no keywords searches all newly posted studies
keywords	array	Full-text terms, each queried separately
sponsor	string	Optional sponsor name, applied to every query
locationCountry	string	Optional exact country filter; any one study location must match it together with any supplied state filter
locationState	string	Optional exact state filter; any one study location must match it together with any supplied country filter
statuses	array	ClinicalTrials.gov overall-status values such as RECRUITING or COMPLETED. Validated by the Actor
postedSince	string	YYYY-MM-DD start date. Overrides the previous successful run's watermark
maxResults	integer	Maximum records per run (1–1000). Default: 100

An unsupported status value fails the run with a clear error rather than silently returning nothing.

How monitoring works (first run and scheduling)

The first run searches the last 14 days by first-posted date unless postedSince is supplied. To keep the watermark and the seen-NCT-ID list across runs, schedule this Actor as a saved Task so runs share the same storage — both live in the task's key-value store. A fresh unsaved run starts a fresh baseline.

The dataset contains the window, not a strict delta. Studies first posted on the boundary date can appear in two consecutive runs; newSinceLastRun is false on the second. Filter on that flag downstream if you only want to alert on studies you have never seen.

Honest limitations

• Each run emits the window, not a strict delta, as above — use newSinceLastRun to separate genuinely new studies from repeats.
• Conditions and keywords are queried separately, then merged. Two conditions means two queries and a union, not an AND across both.
• The window keys on first-posted date. A study registered years ago that was updated yesterday is not "new" by this definition and will not appear.
• briefSummary is truncated to 500 characters. The full text is available on ClinicalTrials.gov via url, and the untruncated protocol section is in raw.
• Locations and central contacts are capped at 25 and 5 respectively. The complete source modules, including site contacts and any further locations, remain inside raw.
• Registry data is sponsor-submitted. Accuracy, completeness and timeliness are the sponsor's, not this Actor's.

Reliability

Diagnostics are written to the RUN_SUMMARY key-value record — never into the dataset. A failed upstream request leaves the watermark and the seen-ID list unchanged, so a transient outage cannot silently skip a window.

Every record carries retrievedAt and a url back to the official registry entry, so you can check any row against the source yourself.

Maintained against the upstream API. If ClinicalTrials.gov changes its schema or an endpoint moves, report it through the Issues tab and it gets fixed.

Integrations

Connect this Actor to Make, Zapier, n8n, Slack, Google Sheets, Airtable or any HTTP endpoint through Apify integrations. A daily Task can post newly registered trials into a research channel, or fire a webhook so a competitive-intelligence digest is assembled the moment a study posts. Datasets export as JSON, CSV, Excel, XML, RSS or HTML.

API usage

curl -X POST "https://api.apify.com/v2/acts/oneshotventure~trials-watch/runs?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"conditions": ["melanoma"], "statuses": ["RECRUITING"], "maxResults": 25}'

Python, JavaScript, PHP and CLI clients are documented under Apify API clients.

Use with AI agents (MCP)

This Actor is callable from any MCP-compatible client — Claude, Cursor, VS Code or your own agent — through the Apify MCP server. The input schema is fully described and every record uses one stable, flat JSON shape, so an agent can call it and read the result without a parsing step. Because it reads the official ClinicalTrials.gov API rather than a rendered page, the answer an agent gets is the same one the source publishes.

Factual registry data. Not medical advice, and not a substitute for reading the study record.

Frequently asked questions

Is there a free ClinicalTrials.gov API?

Yes — the National Library of Medicine publishes an open API for the registry, with no key required. This Actor is the scheduling, multi-query and change-feed layer over it.

How do I track new clinical trials for a condition?

Put the condition in conditions, save the Actor as a Task, and schedule it. Each run returns studies first posted in the new window, with newSinceLastRun marking the ones you have not seen.

How do I monitor a competitor's trial pipeline?

Set sponsor to their name. It is applied to every query, so you can combine it with conditions or keywords to narrow to a therapeutic area.

Can I filter by trial phase or recruitment status?

Recruitment status yes, via statuses. Phase is returned on every record in the phases array but is not an input filter — filter on it downstream.

How often is ClinicalTrials.gov updated?

Continuously, as sponsors submit and update records. This Actor reads the API live at run time, so results are as current as the registry itself.

Does it return site locations or eligibility criteria?

It returns up to 25 normalized site locations and up to 5 central contacts. Eligibility criteria remain inside raw, and the full record is always one click away via url.

Why did a study appear in two runs?

Because the window is inclusive of its start date. The second appearance carries newSinceLastRun: false — filter on that flag to alert only once.

Related actors

• US Product Recalls Monitor — CPSC and FDA food, drug and device enforcement actions.
• NPI Registry Lookup — US healthcare provider search and verification.
• Grants.gov Monitor — new federal research funding opportunities.
• Federal Register Monitor — new FDA and HHS rules and notices.

Disclaimer

This independent tool uses public ClinicalTrials.gov data and is not affiliated with NIH or NLM.