biomcp MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

11+ entity types covering genes, variants, articles, trials, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, GWAS
Deduplication across overlapping sources (PubTator3)
Optional API keys unlock higher rate limits and premium data (NCBI, OncoKB, Semantic Scholar, NCI, OpenFDA)
Install via curl script, PyPI (biomcp-cli), or remote HTTP
Zero-key operation possible — unauthenticated public APIs work by default

Live-Demo

In der Praxis

biomcp.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "biomcp": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/genomoncology/biomcp"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "biomcp": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/genomoncology/biomcp"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "biomcp": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/genomoncology/biomcp"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "biomcp": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/genomoncology/biomcp"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "biomcp",
      "command": "TODO",
      "args": [
        "See README: https://github.com/genomoncology/biomcp"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "biomcp": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/genomoncology/biomcp"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add biomcp -- TODO 'See README: https://github.com/genomoncology/biomcp'

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: biomcp

Triage a patient's gene variant for clinical relevance

👤 Genetic counselors, clinical researchers ⏱ ~15 min advanced

Wann einsetzen: A VCF annotation returned a variant you've never seen — is it actionable?

Voraussetzungen

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

Ablauf

Look up the variant

Look up BRCA2 c.7934del. ClinVar significance, gnomAD frequency, and any CIViC evidence.✓ Kopiert

→ Consolidated card from multiple sources
Pull supporting papers

Find the 3 most cited PubMed articles on this variant.✓ Kopiert

→ Paper list with PMIDs
Check for trials

Any open clinical trials recruiting for BRCA2 mutation carriers?✓ Kopiert

→ Trial list from ClinicalTrials.gov

Ergebnis: A multi-source picture of a variant with evidence pointers.

Fallstricke

Not a substitute for clinical review — Always have a qualified clinician review — this is research aid, not diagnosis
Some sources disagree on variant classification — Surface disagreements explicitly; don't average them

Conduct a targeted literature review

👤 PhD students, MDs, industry researchers ⏱ ~20 min intermediate

Wann einsetzen: You need a bibliography on a specific gene-disease-drug angle.

Ablauf

Search articles

Search PubMed + Europe PMC for 'KRAS G12C AND adagrasib' 2022-2026. Dedupe across sources.✓ Kopiert

→ Deduplicated paper list
Summarize

For the top 10 by citation count, give me title + one-line take-home.✓ Kopiert

→ Annotated bibliography

Ergebnis: A defensible starting bibliography.

Kombinieren mit: filesystem

Check adverse-event profile for a drug

👤 Pharmacy, safety teams ⏱ ~20 min intermediate

Wann einsetzen: Before recommending a drug, check OpenFDA / Drugs@FDA signals.

Ablauf

Query drug

For pembrolizumab: top adverse events per OpenFDA FAERS, last 5 years, broken down by seriousness.✓ Kopiert

→ Ranked AE table
Context

What's the expected AE profile per the FDA label vs FAERS real-world?✓ Kopiert

→ Label vs real-world comparison

Ergebnis: Grounded safety picture combining label and post-market data.

Find clinical trials matching a patient profile

👤 Clinicians, patient advocates ⏱ ~25 min advanced

Wann einsetzen: A patient exhausted standard options and you want to scan for trial matches.

Ablauf

Match trials

Find Phase 2/3 recruiting trials for stage IV NSCLC with EGFR exon 20 insertion, US sites.✓ Kopiert

→ Trial list with NCT IDs
Summarize eligibility

For the top 5, summarize key inclusion/exclusion criteria.✓ Kopiert

→ Per-trial eligibility card

Ergebnis: A prioritized trial match list for clinical discussion.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

biomcp + filesystem

Save evidence memos as local markdown

For variant BRCA2 c.7934del, generate a one-page evidence memo and save to ~/research/brca2-7934.md.✓ Kopiert

biomcp + documentation-server

Build a personal literature library across biomcp queries

Every paper I star via biomcp, also ingest into documentation-server for future RAG queries.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
gene	symbol or id, sources?: str[]	Gene-level lookup	multiple upstream calls
variant	hgvs\|rsid\|position	Variant interpretation	multiple upstream calls
article	query or pmid	Literature search	PubMed/Europe PMC/S2 calls
trial	query/condition/phase/status	Clinical trial match	CT.gov + NCI CTS calls
drug	name or id	Drug profile	multiple calls
disease	name or MONDO id	Disease context	multiple calls
adverse_event	drug or reaction	Safety analysis	OpenFDA calls

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Public APIs default. Optional keys raise limits: NCBI_API_KEY, S2_API_KEY, ONCOKB_TOKEN, OPENFDA_API_KEY, NCI_API_KEY
Tokens pro Aufruf: Consolidated entity responses 1-5k tokens
Kosten in €: Free; some premium sources (OncoKB clinical) require license even with key
Tipp: For heavy literature work, get NCBI_API_KEY (free) — triples PubMed rate.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Env vars per provider key

Datenabfluss: Calls to biomedical public APIs; queries themselves can be sensitive (patient variants etc.)

Queries can include PHI-adjacent data — confirm your deployment's data handling before running on real patient info.
Not a medical device; outputs are research aids only.

Fehlerbehebung

Häufige Fehler und Lösungen

Rate limited on PubMed

Set NCBI_API_KEY for higher limits.

Prüfen: Check NCBI API Key page

OncoKB returns 403

OncoKB requires a token; register at oncokb.org and set ONCOKB_TOKEN.

Prüfen: curl -H 'Authorization: Bearer $ONCOKB_TOKEN' https://www.oncokb.org/api/v1/utils/numbers

No results for a known gene symbol

Some symbols have aliases; try both (e.g. ERBB2 vs HER2).

Prüfen: Search on genecards.org

Alternativen

biomcp vs. andere

Alternative	Wann stattdessen	Kompromiss
Individual databases via direct REST	You only need one source	No deduplication or cross-linking
OpenTargets Platform directly	You primarily care about target-disease evidence	Narrower coverage

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen