Skip to content
ToolCargo

ClinicalTrials.gov Study Research

Live

Research study status, registry dates and posted-results availability.

Find public ClinicalTrials.gov study records and inspect exact NCT IDs. Compare recorded status, sponsor, study type, phases and actual or estimated dates while keeping posted-results availability distinct from study outcomes.

Connect / 2 tools

Server URL

streamable http
https://toolcargo.com/mcp/clinicaltrials

Claude Code

terminal
claude mcp add --transport http --scope user toolcargo-clinicaltrials https://toolcargo.com/mcp/clinicaltrials \
  --header "Authorization: Bearer YOUR_API_KEY"

Create a key in your dashboard. Other clients: setup guides.

What it helps you do

  • Study metadata discovery
  • Exact NCT identity
  • Status and date comparisons

Built for: Research agents preparing source-linked study record comparisons.

Example requests

Compare sleep-apnea study records

“Find sleep apnea study records, inspect two exact NCT IDs and compare overall status, posted-results availability and source dates. Preserve estimated dates and missing fields, cite ClinicalTrials.gov with its processing timestamp and disclose ToolCargo's projection. Do not infer treatment effectiveness or safety.”

A bounded study registry comparison with source identity, timestamp and missing-data disclosures.

Explore useful agent workflows ↗

Tools

ToolWhat it doesAccess
clinicaltrials_search_studies
Find public study records
Search ClinicalTrials.gov selected public metadata by a plain human condition topic and optional overall status. Explicit filter-bound pages of 1–10 records; no contacts, eligibility, narratives, outcomes or participant data. Fetches the source processing timestamp each operation. One shared-plan call.Read-only
clinicaltrials_study_record
Inspect an exact NCT study record
Inspect one canonical eight-digit NCT ID. Preserve source status, independent posted-results availability and actual/estimated month/day dates. Validated source-specific absence only; aliases are not followed. Public registry research, not treatment advice or efficacy/safety findings. One shared-plan call.Read-only

Requirements

  • • A ToolCargo account with Site Audit activated (free). No ClinicalTrials.gov account, key or paid provider.

Limitations

  • • Selected sponsor-submitted registry metadata, not complete protocols, outcomes, participant data, contacts or eligibility. Registration and source review do not establish safety, efficacy, approval or treatment suitability.
  • • Overall status and hasResults are independent. Results availability does not establish outcomes, completeness or a benefit. Source date precision and ACTUAL/ESTIMATED labels remain explicit.
  • • Every operation fetches source version before and after metadata separately, without caching. Processing timestamp is UTC source metadata, not an atomic snapshot or a study update date; matching API version and processing timestamp are required before and after metadata; a detected change fails with an explicit restart message and no retry or finding.
  • • Plain human condition topics only; no Boolean/DSL or NCT-ID search aliases. Explicit cursors bind topic, status, limit, sort and selected fields. Mutable pages may be empty with continuation; later total counts may be missing. Upstream does not echo query identity.
  • • Bounded inert plain text and missing/truncation signals. Fixed HTTPS metadata origin only, 2 MiB/15-second responses and at most 35 seconds per operation, shared 60-second recovery lease, minimum start spacing and source-directed cooldown. No retries or redirects; no published numeric quota is claimed.
  • • ClinicalTrials.gov permits free worldwide access subject to attribution, currentness, processing-date and modification disclosures. International and third-party copyrights remain retained; no blanket CC0, ownership, reuse-clearance or endorsement claim. Check current source terms.

Supported clients

“Tested” means we connected that client to this endpoint and ran a tool call ourselves. Recorded client-specific tests currently cover Site Audit. Other connectors use the documented setup until tested in that client.

Claude CodeAPI key headerDocumented, not yet testedThis endpoint has not yet been tested in this client. See the setup guide.
Claude (claude.ai)OAuth sign-inDocumented, not yet testedThis endpoint has not yet been tested in this client. See the setup guide.
CursorAPI key headerDocumented, not yet testedThis endpoint has not yet been tested in this client. See the setup guide.
VS Code (Copilot agent mode)API key headerDocumented, not yet testedThis endpoint has not yet been tested in this client. See the setup guide.
ChatGPT (developer mode)OAuth sign-inDocumented, not yet testedThis endpoint has not yet been tested in this client. See the setup guide.
MCP InspectorAPI key headerDocumented, not yet testedThis endpoint has not yet been tested in this client. See the setup guide.

Practical workflows

Pricing

Included with Site Audit. Each successful search page or exact record lookup uses one shared-plan call.

Free

$0

Try hosted tools with a shared monthly allowance.

50 shared calls/month

Pro

$12/mo

Proposed larger shared allowance; see checkout status on the pricing page.

2,000 shared calls/month

Proposed test price. See the pricing page for checkout status.

Full pricing and billing details