Description

This MCP server provides AI assistants with unified access to biomedical databases and research tools through a single interface, built by the BioContextAI team using Python with FastMCP and designed to eliminate the need for custom integrations with each biomedical resource. The implementation offers over 20 specialized tools covering protein databases (UniProt, AlphaFold, Human Protein Atlas), genomics resources (Ensembl, KEGG), literature search (Europe PMC, Google Scholar), clinical data (ClinicalTrials.gov, OpenFDA), and ontologies (Gene Ontology, EFO, ChEBI), with both self-hosted deployment options and a hosted service at mcp.biocontext.ai. Built with comprehensive test coverage, Docker support, and integration with the BioContextAI Registry for community tool discovery, it serves researchers needing programmatic access to biomedical data, bioinformatics teams requiring standardized database queries, and AI applications that need verified biomedical information without managing multiple API integrations.

Installation

npx -y biocontext_kb

npm install biocontext_kb

git clone https://github.com/biocontext-ai/knowledgebase-mcp

Claude Desktop Configuration

Add this configuration to your Claude Desktop config file to enable this MCP server:

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json

Config file location: %APPDATA%\Claude\claude_desktop_config.json

Config file location: ~/.config/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "biocontext-knowledgebase": {
      "command": "npx",
      "args": [
        "-y",
        "biocontext_kb"
      ]
    }
  }
}