BioMCP

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

Description

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 suggest "<question>" routes a biomedical question to a shipped worked example and two starter commands.
• 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.

Installation

Binary install

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

PyPI tool install

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

This installs the biomcp binary on your PATH.

Claude Desktop extension (.mcpb)

Install BioMCP from the Anthropic Directory in Claude Desktop when that path is available for your environment. For local/manual setups, use the JSON MCP config below.

Install skills

Install guided investigation workflows into your agent directory:

biomcp skill install ~/.claude --force

MCP clients

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

Remote HTTP server

For shared or remote deployments:

biomcp serve-http --host 127.0.0.1 --port 8080

Remote clients connect to http://127.0.0.1:8080/mcp. Probe routes are GET /health, GET /readyz, and GET /.

Runnable demo:

uv run --script examples/streamable-http/streamable_http_client.py

See Remote HTTP Server for the newcomer guide.

From source

make install
"$HOME/.local/bin/biomcp" --version

For repo-local verification, make check now includes the release-critical Python/docs contract lane (make test-contracts), and make release-gate is the full routine release-readiness command (make check plus deterministic make spec-contracts). Use make release-live-smoke only for opt-in live public-upstream confidence.

Quick start

First useful query in under 30 seconds:

uv tool install biomcp-cli
biomcp health --apis-only
biomcp suggest "What drugs treat melanoma?"
biomcp list gene
biomcp search all --gene BRAF --disease melanoma  # unified cross-entity discovery
biomcp get gene BRAF pathways hpa

Command grammar

search <entity> [filters]    → discovery
suggest <question>           → playbook routing for how-to questions
discover <query>             → concept resolution before entity selection
get <entity> <id> [sections] → focused detail
<entity> <helper> <id>       → cross-entity pivots
enrich <GENE1,GENE2,...>     → gene-set enrichment
batch <entity> <id1,id2,...> → parallel gets
search all [slot filters]    → counts-first cross-entity orientation

Entities and sources

The 13-row table below is the public entity surface; individual rows may use live APIs, local runtime data, or hybrid source overlays.

| Entity | Upstream providers used by BioMCP | Example | |--------|-----------------------------------|---------| | gene | MyGene.info, UniProt, Reactome, QuickGO, STRING, GTEx, Human Protein Atlas, DGIdb, ClinGen, NIH Reporter, DisGeNET, GTR-backed diagnostics pivot | biomcp get gene BRAF pathways hpa | | variant | MyVariant.info, ClinVar, gnomAD fields via MyVariant, CIViC, Cancer Genome Interpreter, OncoKB, cBioPortal, GWAS Catalog, AlphaGenome | biomcp get variant "BRAF V600E" clinvar | | article | PubMed, PubTator3, Europe PMC, PMC OA, NCBI ID Converter, Semantic Scholar (optional auth; S2_API_KEY recommended) | biomcp search article -g BRAF --limit 5 | | trial | ClinicalTrials.gov API v2, NCI CTS API | biomcp search trial -c melanoma -s recruiting | | diagnostic | NCBI Genetic Testing Registry local bulk bundle + WHO IVD local CSV + optional OpenFDA device overlay | biomcp get diagnostic GTR000006692.3 regulatory | | drug | MyChem.info, DDInter local bundle, EMA local batch, WHO Prequalification local exports, ChEMBL, OpenTargets, Drugs@FDA, OpenFDA labels/shortages/approvals/FAERS/MAUDE/recalls, CIViC | biomcp drug interactions warfarin | | disease | MyDisease.info, Monarch Initiative, MONDO, OpenTargets, Reactome, CIViC, SEER Explorer, NIH Reporter, DisGeNET, MedlinePlus clinical_features, GTR/WHO IVD diagnostics pivot | biomcp get disease "Lynch syndrome" genes | | pathway | Reactome, KEGG, WikiPathways, g:Profiler, Enrichr-backed enrichment sections | biomcp get pathway hsa05200 genes | | protein | UniProt, InterPro, STRING, ComplexPortal, PDB, AlphaFold | biomcp get protein P15056 complexes | | adverse-event | OpenFDA FAERS/MAUDE/recalls plus CDC WONDER VAERS aggregate vaccine search | biomcp search adverse-event --drug pembrolizumab | | pgx | CPIC, PharmGKB | biomcp get pgx CYP2D6 recommendations | | gwas | GWAS Catalog | biomcp search gwas --trait "type 2 diabetes" | | phenotype | Monarch Initiative (HPO semantic similarity) | biomcp search phenotype "HP:0001250" |

Cross-entity helpers

Pivot between related entities without rebuilding filters.

See the cross-entity pivot guide for when to use a helper versus a fresh search.

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 drugs hsa05200
biomcp pathway articles R-HSA-5673001
biomcp pathway trials R-HSA-5673001
biomcp protein structures P15056
biomcp article entities 22663011
biomcp article citations 22663011 --limit 3
biomcp article references 22663011 --limit 3
biomcp article recommendations 22663011 --limit 3

Gene-set enrichment

biomcp enrich BRAF,KRAS,NRAS --limit 10

Top-level biomcp enrich uses g:Profiler. Gene enrichment sections inside other entity views still reference Enrichr where that is the backing source.

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 BRCA1 diagnostics       # diagnostic-test pivot from GTR
biomcp get gene BRAF hpa                # protein tissue expression + localization
biomcp get gene BRAF civic interactions # multiple sections
biomcp get gene BRAF all                # standard sections; diagnostics/funding stay opt-in

biomcp get variant "BRAF V600E" clinvar population conservation
biomcp get article 22663011 tldr
biomcp get drug pembrolizumab label targets civic approvals
biomcp get drug trastuzumab regulatory --region who
biomcp get disease "Lynch syndrome" genes phenotypes variants
biomcp get disease tuberculosis diagnostics
biomcp get diagnostic GTR000006692.3 regulatory
biomcp get trial NCT02576665 eligibility locations outcomes

In JSON mode, get responses expose _meta.next_commands for the next likely follow-ups and _meta.section_sources for section-level provenance. batch ... --json returns per-entity objects with the same metadata shape.

API keys

Most commands work without credentials. Optional keys improve rate limits or unlock optional enrichments:

export NCBI_API_KEY="..."        # PubTator, PubMed/efetch, PMC OA, NCBI ID converter
export S2_API_KEY="..."          # Optional Semantic Scholar auth; dedicated quota at 1 req/sec
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

search article, get article, article batch, get article ... tldr, and the explicit Semantic Scholar helpers all work without S2_API_KEY. With the key, BioMCP sends authenticated requests and uses a dedicated rate limit at 1 req/sec. Without it, BioMCP uses the shared unauthenticated pool at 1 req/2sec. search article --source supports all, pubtator, europepmc, and pubmed. The default compatible article federation uses PubTator3, Europe PMC, and PubMed, while the S2 leg remains automatic rather than directly selectable. References and recommendations can be empty for paywalled papers because of publisher elision in Semantic Scholar upstream coverage.

Configuration

Claude Desktop extension settings

The directory bundle exposes only the optional settings needed for the first reviewer-facing build:

| Claude Desktop field | Runtime env var | Purpose | |----------------------|-----------------|---------| | OncoKB Token |