Atlas / MCP servers / jamesanz / Medical

MedicalSAFE

Name: Medical
Author: jamesanz

mcp/jamesanz/medical

MCP server by jamesanz · fda · google scholar · llms · Audited 2026-10-07

An MCP server that provides comprehensive medical information by querying multiple authoritative medical APIs including FDA, WHO, PubMed, Google Scholar, and RxNorm

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

17 17r · 0w · 0d

Transport

stdio · streamable-http

License

MIT

Stars

114

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Bring trusted medical data directly into your AI workflow. A local server for private, free access to FDA, WHO, PubMed, RxNorm, Semantic Scholar, and Google Scholar. No API keys. No data leaks.

An MCP (Model Context Protocol) server that brings authoritative medical information into AI coding environments like Cursor and Claude Desktop.

[](https://archestra.ai/mcp-catalog/jamesanz__medical-mcp)

Why Use Medical MCP?

🔒 Your Data Never Leaves – Runs 100% locally; no tracking, no logs, no cloud
🆓 No API Keys – Works out of the box, zero configuration
🏥 Authoritative Sources – FDA, TGA, Health Canada, EMA, DailyMed, WHO, PubMed, RxNorm, ClinicalTrials.gov
⚡ Easy Setup – One-click install in Cursor or simple manual setup
🔬 Comprehensive – Drug info, health stats, medical literature, clinical guidelines, pediatric sources
🛡️ Resilient – Circuit breakers, retry with backoff, rate limiting, and automatic fallbacks
📊 Evidence-Graded – Results tagged with study type and evidence level (Meta-Analysis → Case Report). Tags are automatic labels from the title and abstract, not independently checked grades.
🏥 Health Monitoring – Built-in health check tool to diagnose source availability

What's New in v2.0

Resilience Layer – Circuit breakers per source, retry with exponential backoff + jitter, per-source token bucket rate limiters
Monid web search – Scholar, AAP, and PMC HTML go through Monid TinyFish (Tavily-style search/fetch). Semantic Scholar is the no-key fallback
Evidence Grading – PubMed and multi-database results tagged with study type (

Read from source at commit 7c8c15b1c1f8OBSERVED · 2026-10-07

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add medical-mcp --env MONID_API_KEY=${MONID_API_KEY} --env NCBI_API_KEY=${NCBI_API_KEY} --env TINYFISH_API_KEY=${TINYFISH_API_KEY} --env TYPESAFE_API_KEY=${TYPESAFE_API_KEY} -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "medical-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "MONID_API_KEY": "${MONID_API_KEY}",
        "NCBI_API_KEY": "${NCBI_API_KEY}",
        "TINYFISH_API_KEY": "${TINYFISH_API_KEY}",
        "TYPESAFE_API_KEY": "${TYPESAFE_API_KEY}"
      }
    }
  }
}

Exposed tools (17)

17 read · 0 write · 0 destructive.

Tool	Risk	Description
`get-article-details`	read	Get detailed information about a specific medical article by PMID. Full text is attached only when the PMC record
`get-cache-stats`	read	Get cache statistics including hit rate, total entries, and memory usage
`get-health-statistics`	read	Get health statistics and indicators from WHO Global Health Observatory
`health-check`	read	Check the health and availability of all upstream data sources (FDA, TGA, Health Canada, EMA, PubMed, WHO, RxNorm, ClinicalTrials, Semantic Scholar, TinyFish). Reports build string, latency, circuit breaker states, and cache health.
`list-sources`	read	List medical data sources and which MCP tools reach them. Includes registry adapters and dedicated-tool sources (WHO, PubMed, RxNorm, Scholar). Not limited to the search-drugs regulator fanout.
`rank-search-hits`	read	Reorder already-fetched literature hits for a clinical question. Retrieval ranking only — never diagnoses, doses, or advises.
`search-clinical-guidelines`	read	Search for clinical guidelines and practice recommendations from medical organizations
`search-clinical-trials`	read	Search ClinicalTrials.gov for trials by condition, intervention, or drug
`search-drug-nomenclature`	read	Search for drug information using RxNorm (standardized drug nomenclature)
`search-drug-safety`	read	Search pharmacovigilance data: FDA FAERS adverse events, recalls, and drug shortages
`search-drugs`	read	Search national drug regulators (FDA, DailyMed, TGA, Health Canada, EMA). Defaults to US, AU, CA, and EU. Pass countries: [
`search-google-scholar`	read	Search for academic research articles using Google Scholar
`search-medical-journals`	read	Search specific medical journals (NEJM, JAMA, Lancet, BMJ, Nature Medicine) for high-quality research
`search-medical-literature`	read	Search for medical research articles in PubMed. Optional question/rerank reorders hits for the question (retrieval only — not diagnosis or advice).
`search-pediatric-drugs`	read	Search for drugs with pediatric labeling and dosing information from FDA database
`search-pediatric-guidelines`	read	Search AAP pediatric guidelines. Policy statements and clinical reports come from PubMed (Pediatrics / AAP corporate author). Bright Futures and publications.aap.org web hits are kept only if the URL is on an AAP host with a real article path.
`search-pediatric-literature`	read	Search for research articles in major pediatric journals (Pediatrics, JAMA Pediatrics, etc.). Optional question/rerank reorders hits for the question (retrieval only — not diagnosis or advice).

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED