search-drugsLABSCO SUMMARY
Every answer traces back to a source you can name.
The value is not that a model can talk about medicine — it already will. It is that a drug answer comes from the FDA record, a prevalence figure from WHO, and a claim from a PubMed citation with a PMID you can open. The paediatric tools are the unusual part: dosing, AAP guidelines and child health indicators are separated out rather than buried in general search.
What it is
A local MCP server that queries named medical sources directly — the FDA drug database, WHO's Global Health Observatory, PubMed, RxNorm, Google Scholar and the American Academy of Pediatrics. Queries run in real time and nothing is stored.
What you get
- Drugs:
search-drugsagainst the FDA database by brand or generic name,get-drug-detailsby NDC code,search-drug-nomenclaturefor standardised RxNorm names - Population data:
get-health-statisticsfor WHO indicators such as life expectancy, mortality and disease prevalence, by country - Literature:
search-medical-literatureover PubMed,get-article-detailsby PMID,search-google-scholar,search-medical-databasesacross PubMed, Scholar, Cochrane and ClinicalTrials.gov, andsearch-medical-journalsfor NEJM, JAMA, Lancet, BMJ and Nature Medicine - Clinical practice:
search-clinical-guidelines - Paediatrics as a first-class area:
search-pediatric-guidelines,search-aap-guidelines,search-pediatric-literature,search-pediatric-drugsfor pediatric labelling and dosing, andget-child-health-statistics - A cache with per-source lifetimes — FDA 24 hours, PubMed 1 hour, WHO 7 days, RxNorm 30 days — readable through
get-cache-statsand tunable withCACHE_ENABLED,CACHE_MAX_SIZEand theCACHE_TTL_*variables
Requirements
Node.js 18+ and npm; npm install -g medical-mcp, a one-click Cursor link, or a build from source. The package is medical-mcp. No keys and no accounts — every source is reached without credentials. One asymmetry worth knowing: Google Scholar is reached by rate-limited web scraping while the other sources use official APIs, so Scholar is the part most likely to fail. It is a reference tool, not medical advice.
Setup effort
One command — npm install -g medical-mcp
USE CASES
01
Checking what a medication actually is
Search the FDA record by brand name, then pull the full detail by NDC code and the standardised name from RxNorm.
02
Doing a literature pass without a paywall
Search PubMed and Scholar on the topic, then fetch the details of the papers worth reading by PMID.
03
Answering a paediatric dosing question
Search drugs carrying paediatric labelling, then check the AAP and Bright Futures guidance beside it.
04
Comparing countries on one indicator
Pull the WHO figure by indicator name and country instead of trusting a recalled number.
16 tools
Listed in project docs. Your client may show a different list.
get-drug-detailssearch-drug-nomenclatureget-health-statisticssearch-medical-literatureget-article-detailssearch-google-scholarsearch-medical-databasessearch-medical-journalssearch-clinical-guidelinessearch-pediatric-guidelinessearch-pediatric-literatureget-child-health-statisticssearch-pediatric-drugssearch-aap-guidelinesget-cache-statsBEFORE YOU INSTALL
What to know first
Tools you get
16 tools named in the project's documentation.
Requires
npm on PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g medical-mcpMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"medical-mcp": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MEDICAL_MCP>/build/index.js"
]
}
}
}
