💊 ClinicalTrials Sponsor Intelligence: Pipeline + FDA Cross Reference

Overview

ClinicalTrials Sponsor Intelligence turns the ClinicalTrials.gov registry into a pharma pipeline research tool. Give it a sponsor (Pfizer, AstraZeneca, Moderna) or a condition (lung cancer, atrial fibrillation, type 2 diabetes) and it returns every completed or terminated trial with phase, status, start date, completion date, lead sponsor, and intervention.

For each completed trial it can also cross reference openFDA drug approvals to flag whether the intervention later received an NDA or BLA clearance. That turns raw registry rows into pipeline outcomes: what worked, what stalled, what shipped. No API key. Pay only per trial delivered.

Reliability posture: blocked, empty, or failed runs are never charged. You only pay for a trial record that was actually delivered.

✅ No login required | ✅ No API key | ✅ FDA approval cross reference | ✅ MCP-ready for AI agents

Features

Sponsor and condition search across ClinicalTrials.gov API v2. Filter by phase (PHASE1 through PHASE4) and enrollment status. Automatic openFDA drug approval flag on every completed trial. Structured JSON output ready for a spreadsheet, dashboard, or LLM. Zero charge on empty runs, first 10 trials free for life.

How it works

The actor queries the public ClinicalTrials.gov API v2 for trials that match the sponsor and/or condition you provide, then applies your phase and status filters. Sponsor search covers both the lead sponsor and any collaborators, so a university, NIH institute, or CRO name will surface every trial they touched.

When crossRefFDA is on, each trial's first intervention name is checked against the openFDA drug approvals database by brand name. A true flag means the drug name appears in FDA approvals: it is a strong signal to investigate further, not a definitive confirmation that the specific indication was approved.

🧾 Input configuration

{
  "sponsor": "Pfizer",
  "condition": "lung cancer",
  "phase": "PHASE3",
  "status": "COMPLETED,TERMINATED",
  "crossRefFDA": true,
  "maxResults": 100
}

📤 Output format

{
  "nct_id": "NCT06704724",
  "title": "A Study to Learn About the Study Medicine PF-07985045 When Given Alone or With Other Anti-cancer Therapies in People With Advanced Solid Tumors That Have a Change in a Gene.",
  "phase": "PHASE1",
  "overall_status": "TERMINATED",
  "start_date": "2024-12-10",
  "completion_date": "2026-05-12",
  "lead_sponsor": "Pfizer",
  "interventions": "DRUG:PF-07985045; COMBINATION_PRODUCT:Gemcitabine; COMBINATION_PRODUCT:Nab-paclitaxel; COMBINATION_PRODUCT:Cetuximab; COMBINATION_PRODUCT:Fluorouracil; COMBINATION_PRODUCT:Oxaliplatin; COMBINATION_PRODUCT:Leucovorin; COMBINATION_PRODUCT:Bevacizumab; COMBINATION_PRODUCT:Pembrolizumab; COMBINATION_PRODUCT:Sasanlimab; COMBINATION_PRODUCT:pemetrexed; COMBINATION_PRODUCT:Cisplatin; COMBINATION_PRODUCT:Paclitaxel; COMBINATION_PRODUCT:Carboplatin; COMBINATION_PRODUCT:PF-07284892",
  "fda_approved": false,
  "url": "https://clinicaltrials.gov/study/NCT06704724",
  "scraped_at": "2026-07-15T04:14:57.888Z"
}

Every trial record contains these fields:

Field	Description
🆔 nct_id	ClinicalTrials.gov identifier (NCT number)
📝 title	Official study title
🧪 phase	Trial phase: PHASE1, PHASE2, PHASE3, or PHASE4
📶 overall_status	Enrollment status: COMPLETED, TERMINATED, RECRUITING, etc.
🗓️ start_date	Study start date (YYYY-MM)
🏁 completion_date	Primary completion date (YYYY-MM)
📄 results_first_posted	Date results were first posted to the registry, when available
🏢 lead_sponsor	Lead sponsor organization name
💉 interventions	Intervention type and name (e.g. DRUG:Lorlatinib)
✅ fda_approved	Whether the intervention appears in openFDA drug approvals
🔗 url	Direct link to the ClinicalTrials.gov study page
⏱️ scraped_at	ISO timestamp of when the record was captured

💼 Common use cases

Pharma business development Track a competitor's late stage pipeline from Phase 3 completion through to approval. Flag which programs delivered and which ones went cold.

Biotech investment research Screen every trial run by a clinical stage company, filter to completed Phase 2 and Phase 3 studies, and see which interventions crossed the FDA line.

Licensing and in licensing scouts Find drugs with positive late stage data that never made it to market: potential asset acquisition targets sitting inside academic or small biotech sponsors.

Regulatory affairs and due diligence Assemble a full trial history for a target company or asset in one run, with the FDA approval status attached to each program.

🚀 Getting started

1. Open the actor and set sponsor to the company or institution you want to track.
2. Optionally add a condition to narrow to one therapy area, and a phase to focus on late stage programs.
3. Leave status at the default COMPLETED,TERMINATED to see only trials with known outcomes.
4. Keep crossRefFDA on for approval enrichment, or turn it off for a faster, cheaper metadata only pull.
5. Click Start, then export the dataset as JSON, CSV, or Excel, or pull it via API or MCP.

FAQ

How accurate is the FDA cross reference? The actor matches the trial's first intervention name against the openFDA drug approvals database by brand name. A true result means the drug name appeared in FDA approvals: it is a strong signal, not a definitive confirmation. Verify the specific indication and approval date manually before acting on it.

Can I search by collaborator instead of lead sponsor? Yes. The sponsor field searches both lead sponsors and collaborators on ClinicalTrials.gov. Enter a university, NIH institute, or CRO name to find every trial where they appear in any sponsor role.

How do I surface terminated trials for competitive intelligence? Set status to TERMINATED and sponsor to the company name. Terminated trials with interventions that were never approved often reveal pipeline failures: valuable input for competitive intelligence and licensing due diligence.

Can I use this without the FDA cross reference? Yes. Set crossRefFDA to false to retrieve trials without the FDA lookup step. That path is faster and cheaper when you only need pipeline metadata.

Can I use it inside an AI agent? Yes. It is exposed as an MCP tool. See below.

Use in Claude, ChatGPT & any MCP agent

https://mcp.apify.com/?tools=themineworks/clinicaltrials-sponsor-intelligence

Or call it programmatically with the Apify client:

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });

const run = await client.actor('themineworks/clinicaltrials-sponsor-intelligence').call({
  sponsor: 'Pfizer',
  condition: 'lung cancer',
  phase: 'PHASE3',
  crossRefFDA: true,
  maxResults: 50,
});

const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

🛠️ Complete your pharma intelligence pipeline

Pair this actor with the rest of the themineworks life sciences suite:

• ClinicalTrials Bulk Exporter: pull large trial slices by keyword without the FDA enrichment step.
• FDA 510(k) Scraper: track medical device clearances by applicant and product code.
• FDA Recalls Scraper: monitor Class I, II, and III drug and device recalls by firm and reason.

Typical flow: clinicaltrials-sponsor maps the pipeline, fda-510k and fda-recalls close the loop on regulatory outcomes.

Found a bug or have a feature request? Open an issue on the actor's Apify Console page or reach out through the Apify profile.