Happy slice of mcp pizzaMCP.pizza

biomcp

MCP.Pizza Chef: genomoncology

Roughly thirty medical and genetic sources, among them PubMed, ClinicalTrials.gov, ClinVar, OncoKB and Reactome, normally each have their own search box and their own quirks. BioMCP puts one question in front of all of them, so your assistant can find trials still recruiting for a condition, look up what a gene variant is known to do, or follow the citation trail out from a single paper. It works with Claude Desktop, Claude Code and Codex, needs no account for the main sources, and was updated as recently as August 2026.

Data
Web/Research

Use This MCP server To

Find clinical trials still recruiting for a specific condition Look up what a gene variant is known to cause Search recent medical papers about a treatment Check known interactions between two medicines Trace the papers that cite a study I already have Gather evidence on a diagnosis before a doctor's appointment

README

BioMCP

One binary. One grammar. Evidence from the biomedical sources you already trust.

What is BioMCP?

BioMCP is one CLI binary over a single command grammar that reaches ~30 trusted biomedical sources (PubMed, ClinVar, ClinicalTrials.gov, OncoKB, Reactome, and more). It is also an MCP (Model Context Protocol) server, so the same tools are available to AI agents such as Claude Code, Codex, and Claude Desktop.

BioMCP cuts through the usual biomedical data maze: one query reaches the sources that normally live behind different APIs, identifiers, and search habits. Researchers, clinicians, and agents use the same command grammar to search, focus, and pivot without rebuilding the workflow for each source. You get compact, evidence-oriented results across live public data plus local study analytics.

Features

  • Search the literature: search article fans out across PubTator3 and Europe PMC, deduplicates PMID/PMCID/DOI identifiers, and can add a Semantic Scholar leg when your filters support it.
  • Pivot without rework: move from a gene, variant, drug, disease, pathway, protein, or article straight into the next built-in view instead of rebuilding filters by hand.
  • Choose a playbook: biomcp skill list shows shipped worked examples so you can open the matching biomcp skill <slug> workflow.
  • Analyze studies locally: study commands cover local query, cohort, survival, compare, and co-occurrence workflows with native terminal, SVG, and PNG charts for downloaded cBioPortal-style datasets.
  • Follow the paper trail: article citations, article references, article recommendations, and article entities turn one known paper into a broader evidence map.
  • Enrich and batch: use biomcp enrich for top-level g:Profiler enrichment and biomcp batch for up to 10 focused get calls in one command.

Quick start

First useful query in under 30 seconds:

uv tool install biomcp-cli
biomcp health --apis-only
biomcp skill list
biomcp list gene
biomcp search all --gene BRAF --disease melanoma  # unified cross-entity discovery
biomcp get gene BRAF pathways hpa

Installation

Binary install

biomcp FAQ

Do I need a paid key?
Not for the main sources. One optional key adds Semantic Scholar results, but the core searches work without any account.
Which apps does it work in?
Claude Desktop, Claude Code and Codex are all documented, and there is a ready-made plugin for Claude Code.
Can I use this to find a trial I might qualify for?
Yes. You can search ClinicalTrials.gov by condition and recruiting status. It is a research aid, not medical advice.
How hard is setup?
You install a command-line program first, which is one line in a terminal, then paste a short block into your app's settings.
Is the information current?
It queries the live public sources each time rather than a stored copy, so results reflect what those sites hold now.
Should I rely on this for medical decisions?
No. It gathers published evidence for you and a clinician to read. It does not interpret anything for your situation.
Is it still being developed?
Yes, very actively. The most recent code change was in August 2026.