Skip to content
MCP server

Pharma, FDA & ClinicalTrials.gov Intelligence MCP

MCP server giving AI agents live ClinicalTrials.gov, OpenFDA and PubMed lookups for pharma

Answers · sign-in required

The server answered 3 hours ago with a sign-in request (HTTP 401), so we could not list its tools.

Install
Pricing
Paid
Platforms
API, CLI, Web
Runs
Remotely
Access
Needs an account or API key
Version
1.0.0
Listing updated
today

Similar MCP servers

About Pharma, FDA & ClinicalTrials.gov Intelligence MCP

Pharma, FDA & ClinicalTrials.gov Intelligence MCP is a paid MCP server for health and science. It runs as a hosted remote server, so there is nothing to install locally.

The README describes a remote MCP endpoint that gives an AI assistant five tools across three US government and biomedical sources: ClinicalTrials.gov v2 for trial search and protocol details, OpenFDA for drug approvals, adverse event reporting and enforcement recalls, and NCBI PubMed for literature citations. Results are returned as compact JSON so that large raw FAERS records do not overwhelm a model's context window.

The server is hosted on Apify and reached over Streamable HTTP, so clients such as Claude Desktop, Cursor or Codex connect with a URL and an Apify API token. Discovery calls such as tools/list are not billed; each successful tools/call is metered per event, with lower rates on higher Apify plans. The README states that no OpenFDA, NIH or PubMed keys are needed.

It is aimed at biopharma business development teams, regulatory affairs staff, medical writers and developers building clinical AI workflows. The README stresses that outputs are research and due diligence material, not medical advice, and that FAERS counts do not establish causation.

Install

Run in a terminal

claude mcp add --transport http pharma-fda-clinical-trials-mcp https://church-of-loujess--pharma-fda-clinical-trials-mcp.apify.actor/mcp

Add to Settings → Connectors → Add custom connector

https://church-of-loujess--pharma-fda-clinical-trials-mcp.apify.actor/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "pharma-fda-clinical-trials-mcp": {
      "url": "https://church-of-loujess--pharma-fda-clinical-trials-mcp.apify.actor/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "pharma-fda-clinical-trials-mcp": {
      "type": "http",
      "url": "https://church-of-loujess--pharma-fda-clinical-trials-mcp.apify.actor/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pharma-fda-clinical-trials-mcp": {
      "serverUrl": "https://church-of-loujess--pharma-fda-clinical-trials-mcp.apify.actor/mcp"
    }
  }
}

Add to Grok Bot desktop app → Connect apps → Add a custom connector

https://church-of-loujess--pharma-fda-clinical-trials-mcp.apify.actor/mcp

Enter a Name (for example "Pharma, FDA & ClinicalTrials.gov Intelligence MCP"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin. When we checked, this server asked for sign-in. Add the credentials it needs under HTTP headers or in the OAuth fields, as its docs describe.

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "pharma-fda-clinical-trials-mcp": {
      "type": "http",
      "url": "https://church-of-loujess--pharma-fda-clinical-trials-mcp.apify.actor/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (5)

Taken from the project documentation; the running server may differ.

search_clinical_trials
Search ClinicalTrials.gov v2 and return NCT IDs, titles, phases, enrollment, sponsors, completion dates, interventions and primary outcomes.
get_trial_details
Fetch full study protocol, summaries, eligibility criteria, study design, dosing arms and endpoints for an NCT ID.
analyze_competitive_pipeline
Aggregate up to 50 live trials in an indication into phase counts, status breakdown, top sponsors, top molecules and upcoming readouts.
detect_fda_adverse_events_and_recalls
Query OpenFDA for Drugs@FDA approvals, FAERS top MedDRA reaction counts with serious outcome split, and FDA drug recalls.
search_pubmed_clinical_evidence
Search NCBI PubMed and return PMIDs, titles, journals, DOIs, authors, dates and PubMed URLs.

What it does

Clinical trial search
Searches ClinicalTrials.gov v2 by condition, intervention, sponsor, phase and recruitment status.
Full protocol details
Returns eligibility criteria, dosing arms, primary and secondary endpoints and site summaries for a given NCT ID.
Competitive pipeline summary
Aggregates sampled trials in an indication into phase counts, sponsor shares and upcoming primary completion dates.
Adverse event and recall lookup
Summarises top MedDRA reaction counts, serious outcome splits, Drugs@FDA approvals and FDA enforcement recalls for a drug.
PubMed citation search
Returns PMIDs, DOIs, journals, authors and dates for matching biomedical literature.
Compact LLM-sized responses
Aggregates server-side so the model receives short payloads instead of multi-megabyte raw FAERS records.

Good for

  • Mapping the Phase 2 and Phase 3 competitor landscape for a disease area before a deal review
  • Summarising reported adverse reactions and recall history for a marketed drug
  • Finding PubMed citations with DOIs to support a clinical background section
  • Checking recruiting or not-yet-recruiting trials by sponsor for outreach research
  • Monitoring FDA enforcement recalls for a list of drugs on a scheduled run

Pricing

Paid

Pay per successful tool call; discovery calls free. Free trial tier returns masked records; per-call rates drop on higher Apify plans.

Prices change. Check apify.com before you buy.

Pharma, FDA & ClinicalTrials.gov Intelligence MCP FAQ

Do I need API keys for OpenFDA, NIH or PubMed?

No. The README says no FDA, NIH or PubMed keys are needed; only an Apify API token is used to authenticate to the endpoint.

Are tools/list and initialize calls billed?

No. The README says initialize, notifications/initialized, tools/list and ping are free, and only successful tools/call executions are charged.

Do FAERS counts prove a drug causes a side effect?

No. The README cites FDA guidance that FAERS reports are spontaneous and do not by themselves establish causal incidence rates.

Which MCP protocol versions are supported?

The README lists support for MCP protocol versions 2025-06-18, 2025-03-26 and 2024-11-05 over Streamable HTTP.

Is Pharma, FDA & ClinicalTrials.gov Intelligence MCP free?

No. Pharma, FDA & ClinicalTrials.gov Intelligence MCP is a paid product.

How do I add Pharma, FDA & ClinicalTrials.gov Intelligence MCP to Claude Code?

Run this command in your terminal: claude mcp add --transport http pharma-fda-clinical-trials-mcp https://church-of-loujess--pharma-fda-clinical-trials-mcp.apify.actor/mcp

What are the best alternatives to Pharma, FDA & ClinicalTrials.gov Intelligence MCP?

The closest alternatives to Pharma, FDA & ClinicalTrials.gov Intelligence MCP are OpenLandscape, MedicineData MCP, Peptency research library, PubMed Scraper and Open Drug Data.

Where this comes from

  • Description: written from the project's README, the project's website and its MCP Registry entry.
  • Status: checked automatically by AIPoweredBot on 19 November 2026.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers