databasesanalytics-data

BioMCP (Biomedical Database Integration)▌

by genomoncology

BioMCP integrates ClinicalTrials.gov, PubMed, and MyVariant.info for unified biomedical database access with structured,

Integrates with biomedical databases including ClinicalTrials.gov, PubMed, and MyVariant.info to provide structured access to clinical trials, research articles, and genetic variants with intelligent data rendering and source attribution.

github stars

★ 456

GitHub Website npm

15+ integrated biomedical databasesSingle binary with unified query grammarBuilt-in guided investigation workflows

best for

/ Biomedical researchers investigating diseases and treatments
/ Bioinformatics analysts working with genetic data
/ Clinical researchers reviewing trials and literature
/ Drug discovery teams analyzing targets and pathways

capabilities

/ Search PubMed articles and clinical trials
/ Query genetic variants from ClinVar and gnomAD
/ Retrieve gene information from MyGene.info and UniProt
/ Cross-reference entities across 15+ biomedical databases
/ Perform gene-set enrichment analysis
/ Batch query multiple entities in parallel

what it does

Queries biomedical databases like PubMed, ClinicalTrials.gov, and genetic variant databases through a unified command interface. Provides structured access to research articles, clinical trials, genes, variants, drugs, and diseases with cross-referencing capabilities.

about

BioMCP (Biomedical Database Integration) is an official MCP server published by genomoncology that provides AI assistants with tools and capabilities via the Model Context Protocol. BioMCP integrates ClinicalTrials.gov, PubMed, and MyVariant.info for unified biomedical database access with structured, It is categorized under databases, analytics data.

how to install

You can install BioMCP (Biomedical Database Integration) in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.

license

MIT

BioMCP (Biomedical Database Integration) is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.

readme

BioMCP

BioMCP is a single-binary CLI and MCP server for querying biomedical databases. One command grammar, compact markdown output, 12 entities across 15+ data sources.

Install

PyPI tool install

uv tool install biomcp-cli
# or: pip install biomcp-cli

This installs the biomcp binary on your PATH.

Binary install

curl -fsSL https://biomcp.org/install.sh | bash

Install skills

Install guided investigation workflows into your agent directory:

biomcp skill install ~/.claude --force

MCP clients

{
  "mcpServers": {
    "biomcp": {
      "command": "biomcp",
      "args": ["serve"]
    }
  }
}

From source

cargo build --release --locked

Quick start

biomcp health --apis-only            # verify API connectivity
biomcp list                          # show all entities and commands
biomcp list gene                     # show gene-specific filters and examples

Command grammar

search <entity> [filters]    → discovery
get <entity> <id> [sections] → focused detail
<entity> <helper> <id>       → cross-entity pivots
enrich <GENE1,GENE2,...>     → gene-set enrichment
batch <entity> <id1,id2,...> → parallel gets

Entities and sources

Entity	Sources	Example
gene	MyGene.info, UniProt, Reactome, QuickGO, STRING, CIViC	`biomcp get gene BRAF pathways`
variant	MyVariant.info, ClinVar, gnomAD, CIViC, OncoKB, cBioPortal, GWAS Catalog, AlphaGenome	`biomcp get variant "BRAF V600E" clinvar`
article	PubMed, PubTator3, Europe PMC	`biomcp search article -g BRAF --limit 5`
trial	ClinicalTrials.gov, NCI CTS API	`biomcp search trial -c melanoma -s recruiting`
drug	MyChem.info, ChEMBL, OpenTargets, Drugs@FDA, CIViC	`biomcp get drug pembrolizumab targets`
disease	Monarch Initiative, MONDO, CIViC, OpenTargets	`biomcp get disease "Lynch syndrome" genes`
pathway	Reactome, g:Profiler	`biomcp get pathway R-HSA-5673001 genes`
protein	UniProt, InterPro, STRING, PDB/AlphaFold	`biomcp get protein P15056 domains`
adverse-event	OpenFDA (FAERS, MAUDE, Recalls)	`biomcp search adverse-event -d pembrolizumab`
pgx	CPIC, PharmGKB	`biomcp get pgx CYP2D6 recommendations`
gwas	GWAS Catalog	`biomcp search gwas --trait "type 2 diabetes"`
phenotype	Monarch Initiative (HPO)	`biomcp search phenotype "HP:0001250"`

Cross-entity helpers

Pivot between related entities without rebuilding filters:

biomcp variant trials "BRAF V600E" --limit 5
biomcp variant articles "BRAF V600E"
biomcp drug adverse-events pembrolizumab
biomcp drug trials pembrolizumab
biomcp disease trials melanoma
biomcp disease drugs melanoma
biomcp disease articles "Lynch syndrome"
biomcp gene trials BRAF
biomcp gene drugs BRAF
biomcp gene articles BRCA1
biomcp gene pathways BRAF
biomcp pathway drugs R-HSA-5673001
biomcp pathway articles R-HSA-5673001
biomcp pathway trials R-HSA-5673001
biomcp protein structures P15056
biomcp article entities 22663011

Gene-set enrichment

biomcp enrich BRAF,KRAS,NRAS --limit 10

Sections and progressive disclosure

Every get command supports selectable sections for focused output:

biomcp get gene BRAF                    # summary card
biomcp get gene BRAF pathways           # add pathway section
biomcp get gene BRAF civic interactions # multiple sections
biomcp get gene BRAF all                # everything

biomcp get variant "BRAF V600E" clinvar population conservation
biomcp get drug pembrolizumab label targets civic approvals
biomcp get disease "Lynch syndrome" genes phenotypes variants
biomcp get trial NCT02576665 eligibility locations outcomes

API keys

Most commands work without credentials. Optional keys improve rate limits:

export NCBI_API_KEY="..."      # PubTator, PMC OA, NCBI ID converter
export OPENFDA_API_KEY="..."   # OpenFDA rate limits
export NCI_API_KEY="..."       # NCI CTS trial search (--source nci)
export ONCOKB_TOKEN="..."      # OncoKB variant helper
export ALPHAGENOME_API_KEY="..." # AlphaGenome variant effect prediction

Multi-worker deployment

BioMCP rate limiting is process-local. For many concurrent workers, run one shared biomcp serve-http endpoint so all workers share a single limiter budget:

biomcp serve-http --host 0.0.0.0 --port 8080

Skills

14 guided investigation workflows are built in:

biomcp skill list
biomcp skill show 03

#	Skill	Focus
01	variant-to-treatment	Variant annotation to treatment options
02	drug-investigation	Drug mechanism, safety, alternatives
03	trial-searching	Trial discovery and patient matching
04	rare-disease	Rare disease evidence and trial strategy
05	drug-shortages	Shortage monitoring and alternatives
06	advanced-therapies	CAR-T and checkpoint therapy workflows
07	hereditary-cancer	Hereditary cancer syndrome workup
08	resistance	Resistance mechanisms and next-line options
09	gene-function-lookup	Gene-centric function and context
10	gene-set-analysis	Enrichment, pathway, and interaction synthesis
11	literature-synthesis	Evidence synthesis with cross-entity checks
12	pharmacogenomics	PGx gene-drug interactions and dosing
13	phenotype-triage	Symptom-first rare disease workup
14	protein-pathway	Protein structure and pathway deep dive

Ops

biomcp version          # show version and build info
biomcp health           # check all API connectivity
biomcp update           # self-update to latest release
biomcp update --check   # check for updates without installing
biomcp uninstall        # remove biomcp from ~/.local/bin

Documentation

Full documentation at biomcp.org.

License

MIT