Clinical Trials Scraper

News & Research

Operated by Sourcelane✓ verified

A ClinicalTrials.gov scraper and query connector that searches and extracts registered clinical trials by condition, intervention/drug, sponsor, or location using the public ClinicalTrials.gov API. It returns structured trial records (one row per trial) including registry identifiers, brief and official titles, sponsoring organizations, recruitment status and study design (type, phases, enrollment), trial summaries, conditions and keywords, detailed interventions with types, sponsorship and collaborator information, eligibility demographics (sex, age ranges, healthy-volunteer flag), site locations (facility-level city/state/country and list of countries), key dates (start, primary completion, completion, first-posted, last-updated), and counts for sites and enrollment. The connector supports filtering and query-driven retrieval, automatic pagination with a resumable pagination token across runs, and global coverage of registered trials.

Verified Sep 28, 12:10 AM

$0.002

per result

Up to 100 per call. Only pay for results returned; failed calls are refunded.

What people use it for

Pharma & biotech competitive intelligence — track who is running trials for a drug, condition, or mechanism
Patient recruitment — find recruiting trials by condition and location
Investor & business due diligence — map a company's clinical pipeline by phase and status
Systematic reviews & research — build structured results of trials matching precise criteria
Market landscaping — quantify trial activity across conditions, sponsors, and geographies

Trust & reliability

7d uptime trend

Window	Uptime	Success rate	p50	p95
24h	—	—	—	—
7d	—	—	—	—
30d	—	—	—	—

Calling contract

Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.

Call it via Sourcelane

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"clinicaltrials-scraper","params":{"queryTerm":"diabetes","maxItems":5},"maxResults":10}'

Request params

Field	Type	Required	Description
`queryTerm`	string	optional	Free-text search across the whole trial record (e.g. 'GLP-1 obesity'). Combined with the more specific filters below. Leave empty to rely on the filters alone.
`condition`	string	optional	Filter by condition or disease (e.g. 'breast cancer', 'type 2 diabetes').
`intervention`	string	optional	Filter by intervention, drug, or treatment name (e.g. 'semaglutide', 'immunotherapy').
`sponsor`	string	optional	Filter by lead sponsor or organization name (e.g. 'Pfizer', 'Mayo Clinic').
`locationCountry`	string	optional	Filter to trials with a site in this country (e.g. 'United States', 'Germany').
`status`	array	optional	Limit to one or more recruitment statuses. Leave empty for all statuses.
`phase`	array	optional	Limit to one or more trial phases. Leave empty for all phases.
`maxItems`	integer	optional	Maximum number of trials to return. Set 0 for unlimited (paginates until the result set is exhausted or the run nears its timeout). Capped at 100 per call.
`pageId`	string	optional	Paste the NEXT_PAGE_ID value from the previous run's Key-value store to resume fetching results where you left off.

Each result contains

Field	Type	Description
`nctId`	string	Nct Id
`title`	string	Title
`officialTitle`	string	Official Title
`acronym`	string	Acronym
`organization`	string	Organization
`status`	string	Status
`studyType`	string	Study Type
`phases`	array	Phases
`briefSummary`	string	Brief Summary
`conditions`	array	Conditions
`keywords`	array	Keywords
`interventions`	array	—
`leadSponsor`	string	Lead Sponsor
`leadSponsorClass`	string	—
`collaborators`	array	—
`enrollmentCount`	integer	—
`sex`	string	—
`minimumAge`	string	—
`maximumAge`	string	—
`healthyVolunteers`	boolean	—
`standardAges`	array	—
`locationCount`	integer	—
`locations`	array	—
`countries`	array	—
`startDate`	string	—
`primaryCompletionDate`	string	—
`completionDate`	string	—
`lastUpdatePostDate`	string	—
`firstPostDate`	string	—
`studyUrl`	string	—

Use Clinical Trials Scraper from Claude, ChatGPT or Cursor

Pick your tool and connect in under a minute. Then just ask — for example: “What has been reported about solid-state batteries in the last week? Cite sources.”

Connect Claude

Web, desktop and mobile. Paste one URL.

1Copy your personal connector URL
2In Claude open Settings → Connectors → Add custom connector
3Paste the URL and click Add — done

Manual setup (config files, REST, Python) +

Claude Code

Adds the Sourcelane MCP server with your key as a header.

terminal

claude mcp add --transport http sourcelane https://cool-puffin-608.convex.site/mcp \
  --header "Authorization: Bearer sl_live_your_agent_key"

Claude Desktop (config file)

Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.

claude_desktop_config.json

{
  "mcpServers": {
    "sourcelane": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://cool-puffin-608.convex.site/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

Cursor & Windsurf

Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).

mcp.json

{
  "mcpServers": {
    "sourcelane": {
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer sl_live_your_agent_key"
      }
    }
  }
}

VS Code

Save as .vscode/mcp.json. VS Code prompts for your key once.

.vscode/mcp.json

{
  "servers": {
    "sourcelane": {
      "type": "http",
      "url": "https://cool-puffin-608.convex.site/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sourcelane-key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "sourcelane-key",
      "description": "Sourcelane agent key",
      "password": true
    }
  ]
}

ChatGPT Custom GPT (Actions)

Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.

OpenAPI schema URL

https://sourcelane-amber.vercel.app/openapi.json

REST

One POST. Pass maxResults to cap cost.

curl

curl -X POST https://cool-puffin-608.convex.site/v1/call \
  -H "Authorization: Bearer sl_live_your_agent_key" \
  -H "Content-Type: application/json" \
  -d '{"listing":"clinicaltrials-scraper","params":{"queryTerm":"diabetes","maxItems":5},"maxResults":10}'

Python, LangChain, CrewAI, OpenAI Agents SDK…

Wrap the REST call as a tool, or point an MCP client at the endpoint.

python

import requests

res = requests.post(
    "https://cool-puffin-608.convex.site/v1/call",
    headers={"Authorization": "Bearer sl_live_your_agent_key"},
    json={
        "listing": "clinicaltrials-scraper",
        "params": {"queryTerm":"diabetes","maxItems":5},
        "maxResults": 10,
    },
    timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])

Reviews

—

0 reviews

Leave a review

Loading reviews…