ct_get_study
Get detailed study information by NCT ID with AI analysis
LABSCO SUMMARY
The cross-source tools are the reason to install it.
Searching PubMed or ClinicalTrials.gov alone is something a browser does. Asking one question and getting trials, published literature and FDA adverse-event data correlated for the same drug is the part that is tedious by hand, because the three sources use different identifiers and different vocabularies. Treat the output as a research starting point rather than a conclusion — the sources are authoritative, the correlation between them is this server's own.
What it is
An MCP server that puts three medical research sources behind one set of tools, and then adds tools that query all three together. Results are cached — an hour for clinical trials, six hours for literature — so repeated questions in one session do not re-hit the upstream APIs.
What you get
- Clinical trials searched by condition, intervention and page size, and any study read in full by its NCT ID —
ct_search_trials,ct_get_study - PubMed literature searched for papers on a topic —
pm_search_papers - The FDA drug database searched, and adverse events analysed for a drug —
fda_search_drugs,fda_adverse_events - One drug analysed across all three sources at a depth you choose, returning trials, literature and regulatory data together —
research_comprehensive_analysis - A safety picture assembled from trials and FDA data at once, rather than read from each separately —
research_drug_safety_profile - The competitive picture for a drug or condition — what else is in trials, from whom —
research_competitive_landscape
Requirements
No key is needed to start: all three sources are public. PUBMED_API_KEY and FDA_API_KEY are optional and raise the rate limits on those two. Node.js 18+. The npm package name is medical-research-mcp-suite (1.0.0); install from a clone with npm install and npm run build, then point your client at dist/index.js. CACHE_TTL and MAX_CONCURRENT_REQUESTS tune how hard it goes at the upstream APIs.
Setup effort
One command — npx -y github:ezhou89/medical-research-mcp-suite
USE CASES
01
Getting oriented on an unfamiliar drug
Run the combined analysis for the drug and condition, and read trials, literature and regulatory data as one picture instead of three tabs.
02
Checking a drug's safety record
Pull the safety profile across trials and FDA data together, then open the adverse-event detail where something stands out.
03
Finding trials a patient might qualify for
Search by condition and intervention, then read the full record of the studies worth pursuing by their NCT ID.
04
Seeing who else is working on the same thing
Ask for the competitive landscape around a drug or condition to find the other programmes in trials before starting a literature review.
05
Grounding a claim in published work
Search PubMed for the papers behind a finding, and cross-check the trial that produced it.
13 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
ct_search_trials
Search ClinicalTrials.gov for studies with AI-enhanced results
fda_adverse_events
Get adverse event reports for a drug with analysis
fda_search_drugs
Search FDA drug database with safety analysis
pm_search_papers
Search PubMed for research papers with enhanced analysis
research_clinical_details
Detailed clinical trials analysis for specific drug/condition
research_competitive_landscape
Analyze competitive landscape across all databases
research_comprehensive_analysis
Comprehensive analysis combining clinical trials, literature, and safety data
research_drug_safety_profile
Complete drug safety analysis across clinical trials and FDA reports
research_executive_summary
Generate executive summary for drug/condition analysis (context-friendly)
research_literature_details
Detailed literature analysis for specific drug/condition
research_market_details
Detailed market and competitive analysis for specific drug/condition
research_safety_details
Detailed safety and FDA analysis for specific drug
BEFORE YOU INSTALL
What to know first
Tools you get
13 tools when we connected.
Requires
- npx on PATH
- Node.js 18+
CONTEXT COST
Light Standing cost
Rated by the size of the 13 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y github:ezhou89/medical-research-mcp-suiteMCP Clients
Claude Desktop
Clone and build
CLAUDE DESKTOP · TERMINAL
git clone https://github.com/ezhou89/medical-research-mcp-suite.git
cd medical-research-mcp-suite
npm install
cp .env.example .env
npm run buildAdd it to Claude Desktop
<YOUR_PATH_TO_MEDICAL_RESEARCH_MCP_SUITE> is the folder you cloned into.
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"medical-research": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MEDICAL_RESEARCH_MCP_SUITE>/dist/index.js"
]
}
}
}
