Skip to content
BioMCP

BioMCPMCP Server

by GenomOncology
Released
v0.8.25
MIT
Repository Docs
Databases & Data

Summary

Biomedical research MCP server reaching about 30 trusted sources — PubMed, ClinicalTrials.gov, ClinVar, OncoKB and Reactome — through one command grammar.

Features

  • One command grammar over about 30 biomedical sources including PubMed and ClinicalTrials.gov
  • Cross-source article search with PMID/PMCID/DOI deduplication
  • Pivot between gene, variant, drug, disease, pathway, protein and article views
  • Citation, reference and recommendation traversal to build an evidence map
  • Local study analytics: cohort, survival, comparison and co-occurrence with chart output
  • Shipped skill playbooks installable into an agent directory
  • Batch up to ten get calls in a single command
  • Install via binary, Homebrew, Docker or PyPI; serves stdio or HTTP

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "BioMCP" tools will be available.
{
  "mcpServers": {
    "biomcp": {
      "command": "biomcp",
      "args": [
        "serve"
      ]
    }
  }
}

Description

BioMCP is a single binary that puts roughly 30 trusted biomedical sources behind one consistent command grammar, and doubles as an MCP server so agents such as Claude Code, Claude Desktop and Codex can query them directly. It covers PubMed and PubTator3, Europe PMC, ClinicalTrials.gov, ClinVar, OncoKB, Reactome and more — sources that normally each demand their own API, identifier scheme and search conventions.

The design goal is to stop rebuilding a workflow for every database. search article fans out across PubTator3 and Europe PMC, deduplicates PMID, PMCID and DOI identifiers, and can add a Semantic Scholar leg when the filters allow it. From any result you can pivot straight into the next built-in view — gene, variant, drug, disease, pathway, protein or article — instead of hand-rebuilding filters. article citations, article references, article recommendations and article entities turn one known paper into a broader evidence map, and biomcp batch bundles up to ten focused get calls into a single command.

Beyond live lookups, the study commands run local analytics over downloaded cBioPortal-style datasets — query, cohort, survival, comparison and co-occurrence workflows — and render results as native terminal, SVG or PNG charts. biomcp skill list ships worked examples as guided playbooks, and biomcp skill install ~/.claude drops those investigation workflows into an agent directory.

Install via the biomcp.org script, Homebrew, Docker (ghcr.io/genomoncology/biomcp) or PyPI. Note the packaging caveat the project flags itself: install biomcp-cli, not the unrelated biomcp PyPI package. It registers with Claude Code as a plugin, with Codex via codex mcp add, and serves remote deployments over HTTP. MIT licensed and maintained by GenomOncology.

Related MCP Servers

MCP: Patent & Literature Search

by Patsnap

Patsnap's MCP server for searching global patents across WIPO, EPO, USPTO, CNIPA, JPO and KIPO alongside scientific literature, returning records as AI-readable Markdown.

Web & Search

MCP: PubMed

by Andy Brandt

Search PubMed's biomedical literature and read abstracts and open-access full text from an AI client.

Web & Search

MCP: Data Commons MCP Server

by Data Commons

Query public statistics — health, economic, demographic and climate indicators from hundreds of official sources — through the Data Commons knowledge graph, hosted or self-run.

Databases & Data

MCP: Pipeworx

by Pipeworx

Open MCP gateway giving agents live, citable data from 1,300+ verified sources like SEC, FDA, USPTO, and FRED.

Databases & Data
Browse all MCP servers →