Atlas / MCP servers / cicatriiz / Healthcare

HealthcareSAFE

mcp/cicatriiz/healthcare

A Model Context Protocol (MCP) server providing AI assistants with access to healthcare data and medical information tools, including FDA drug info, PubMed, medRxiv, NCBI Bookshelf, clinical trials, ICD-10, DICOM metadata, and a medical calculator.

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
11 11r · 0w · 0d
Transport
stdio
License
MIT
Stars
129
01

Overview

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

[](https://smithery.ai/server/@Cicatriiz/healthcare-mcp-public) A Model Context Protocol (MCP) server providing AI assistants with access to healthcare data and medical information tools.

Overview

Healthcare MCP Server is a specialized Node.js server that implements the Model Context Protocol (MCP) to provide AI assistants with access to healthcare data and medical information tools. It enables AI models to retrieve accurate, up-to-date medical information from authoritative sources. This repository provides a single DXT package containing the complete Node.js implementation.

DXT Extension

This repository includes a packaged DXT (Desktop Extension) file for easy installation in compatible development environments. Download healthcare-mcp.dxt for one-click installation.

Features

  • FDA Drug Information: Search and retrieve comprehensive drug information from the FDA database (improved response parsing)
  • PubMed Research: Search medical literature from PubMed's database of scientific articles
  • Health Topics: Access evidence-based health information from Health.gov (updated to API v4)
  • Clinical Trials: Search for ongoing and completed clinical trials (updated API parameters)
  • Medical Terminology: Look up ICD-10 codes and medical terminology definitions
  • medRxiv Search: Search for pre-print articles on medRxiv
  • Medical Calculator: Calculate Body Mass Index (BMI)
  • NCBI Bookshelf Search: Search the NCBI Bookshelf for biomedical books and documents
  • DICOM Metadata Extraction: Extract metadata from a DICOM file
  • Caching: Efficient caching system with connection pooling to reduce API calls and improve performance
  • Usage Tracking: Anonymous usage tracking to monitor API usage
  • Error Handling: Robust error handling and logging
  • Multiple Interfaces: Support for both stdio (for CLI) and HTTP/SSE inter
Read from source at commit f45167416319OBSERVED · 2026-10-07
02

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 healthcare-mcp-nodejs --env FDA_API_KEY=${FDA_API_KEY} --env NCBI_API_KEY=${NCBI_API_KEY} --env PUBMED_API_KEY=${PUBMED_API_KEY} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "healthcare-mcp-nodejs": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "FDA_API_KEY": "${FDA_API_KEY}",
        "NCBI_API_KEY": "${NCBI_API_KEY}",
        "PUBMED_API_KEY": "${PUBMED_API_KEY}"
      }
    }
  }
}
03

Exposed tools (11)

11 read · 0 write · 0 destructive.

ToolRiskDescription
calculate_bmireadCalculate Body Mass Index (BMI)
clinical_trials_searchreadSearch for clinical trials by condition, status, and other parameters
extract_dicom_metadatareadExtract metadata from a DICOM file
fda_drug_lookupreadLook up drug information from the FDA database
get_all_usage_statsreadGet overall usage statistics for all sessions
get_usage_statsreadGet usage statistics for the current session
health_topicsreadGet evidence-based health information on various topics
lookup_icd_codereadLook up ICD-10 codes by code or description
medrxiv_searchreadSearch for pre-print articles on medRxiv
ncbi_bookshelf_searchreadSearch the NCBI Bookshelf for biomedical books and documents
pubmed_searchreadSearch for medical literature in PubMed database
04

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.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (2 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (4)

LOWInsecure crypto · crypto.weak_hash · CWE-327, CWE-338
server/cache-service.js:31
return crypto.createHash('md5').update(cacheKey).digest('hex');
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, node-fetch, node-cache, sqlite3
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
server/package.json
@modelcontextprotocol/sdk, dicom-parser, node-cache, node-fetch, sqlite3
Why it matters. 5 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOInventory / provenance · inv.oversize · CWE-1104
healthcare-mcp.dxt
healthcare-mcp.dxt
Why it matters. 8976554 bytes not read

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha f45167416319full audit observations/trust-audit/mcp-server/cicatriiz__healthcare.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07f45167416319SAFEB89first audit
06

Questions

What is the Healthcare MCP server?

A Model Context Protocol (MCP) server providing AI assistants with access to healthcare data and medical information tools, including FDA drug info, PubMed, medRxiv, NCBI Bookshelf, clinical trials, ICD-10, DICOM metadata, and a medical calculator.

What tools does Healthcare expose?

11 in total: 11 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Healthcare safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Healthcare need?

It reads FDA_API_KEY, NCBI_API_KEY and PUBMED_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Healthcare run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as healthcare-mcp-nodejs at 2.1.1.

How current is this page?

The grade is for one exact copy of the source (f45167416319), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement