medical-mcp and healthcare-mcp-public
These are complements that serve overlapping but distinct purposes—one provides medical information aggregation across FDA, WHO, PubMed, and RxNorm, while the other extends the scope to include preprints (medRxiv), clinical literature (NCBI Bookshelf), and clinical trials data, making them best used together for comprehensive medical data access within MCP-compatible systems.
About medical-mcp
JamesANZ/medical-mcp
An MCP server that provides comprehensive medical information by querying multiple authoritative medical APIs including FDA, WHO, PubMed, Google Scholar, and RxNorm
Implements an in-memory caching layer with source-specific TTL policies (FDA: 24h, PubMed: 1h, WHO: 7d, RxNorm: 30d) and LRU eviction to reduce API latency from 800-1500ms to <10ms. Runs as a Node.js/TypeScript MCP server compatible with Cursor and Claude Desktop, requiring zero API keys while querying live FDA, WHO, PubMed, RxNorm, Google Scholar, and AAP endpoints with specialized tools for drug nomenclature, health statistics, clinical literature, and pediatric guidelines.
About healthcare-mcp-public
Cicatriiz/healthcare-mcp-public
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.
# Technical Summary Implements stdio and HTTP/SSE transport modes with connection pooling and caching to optimize repeated API calls across nine medical data sources. Built as a Node.js MCP server that wraps FDA, PubMed, Health.gov, Clinical Trials.gov, NCBI, and medRxiv APIs with standardized tool interfaces, enabling AI assistants to retrieve evidence-based medical information while tracking anonymous usage patterns. Deployable via DXT extension package, npm, or source installation with optional Swagger UI for HTTP mode testing.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work