Skip to content

BioMCP: AI-Powered Biomedical Research

Release Build status License

Transform how you search and analyze biomedical data with BioMCP - a powerful tool that connects AI assistants and researchers to critical biomedical databases through natural language.

Built and Maintained by

NEW Remote BioMCP Now Available!

Connect to BioMCP instantly through Claude - no installation required!

🚀 Instant Access Start using BioMCP in under 2 minutes
☁️ Cloud-Powered Always up-to-date with latest features
🔒 Secure Auth Google OAuth authentication
🛠️ 23+ Tools Full suite of biomedical research tools
Connect to Remote BioMCP Now

What Can You Do with BioMCP?

Search Research Literature

Find articles about genes, variants, diseases, and drugs with automatic cancer genomics data from cBioPortal

biomcp article search --gene BRAF --disease melanoma

Discover Clinical Trials

Search active trials by condition, location, phase, and eligibility criteria including genetic biomarkers

biomcp trial search --condition "lung cancer" --status RECRUITING

Analyze Genetic Variants

Query variant databases, predict effects, and understand clinical significance

biomcp variant search --gene TP53 --significance pathogenic

AI-Powered Analysis

Use with Claude Desktop for conversational biomedical research with sequential thinking

# Claude automatically uses BioMCP tools
"What BRAF mutations are found in melanoma?"

5-Minute Quick Start

Choose Your Interface

Best for: Conversational research, complex queries, AI-assisted analysis

  1. Install Claude Desktop from claude.ai/desktop

  2. Configure BioMCP: json { "mcpServers": { "biomcp": { "command": "uv", "args": [ "run", "--with", "biomcp-python", "biomcp", "run" ] } } }

  3. Start researching: Ask Claude about any biomedical topic!

Full Claude Desktop Guide →

Best for: Direct queries, scripting, automation

  1. Install BioMCP:

    # Using uv (recommended)
    uv tool install biomcp
    
    # Or using pip
    pip install biomcp-python
    

  2. Run your first search:

    biomcp article search \
      --gene BRAF --disease melanoma \
      --limit 5
    

CLI Reference →

Best for: Integration, custom applications, bulk operations

  1. Install the package:

    pip install biomcp-python
    

  2. Use in your code:

    from biomcp import BioMCPClient
    
    async with BioMCPClient() as client:
        articles = await client.articles.search(
            genes=["BRAF"],
            diseases=["melanoma"]
        )
    

Python SDK Docs →

Key Features

Unified Search Across Databases

  • PubMed/PubTator3: 30M+ research articles with entity recognition
  • ClinicalTrials.gov: 400K+ clinical trials worldwide
  • MyVariant.info: Comprehensive variant annotations
  • cBioPortal: Automatic cancer genomics integration

Intelligent Query Processing

  • Natural language to structured queries
  • Automatic synonym expansion
  • OR logic support for flexible matching
  • Cross-domain relationship discovery

Built for AI Integration

  • 24 specialized MCP tools
  • Sequential thinking for complex analysis
  • Streaming responses for real-time updates
  • Context preservation across queries

Explore All Features →

Learn by Example

Find Articles About a Specific Mutation

# Search for BRAF V600E mutations
biomcp article search --gene BRAF \
  --keyword "V600E|p.V600E|c.1799T>A"

Discover Trials Near You

# Find cancer trials in Boston area
biomcp trial search --condition cancer \
  --latitude 42.3601 --longitude -71.0589 \
  --distance 50

Get Gene Information

# Get comprehensive gene data
biomcp gene get TP53

More Examples →

Literature Review

Systematic search across papers, preprints, and clinical trials Workflow Guide →

Variant Interpretation

From variant ID to clinical significance and treatment implications Workflow Guide →

Trial Matching

Find eligible trials based on patient criteria and biomarkers Workflow Guide →

Drug Research

Connect drugs to targets, trials, and research literature Workflow Guide →

Advanced Features

Documentation

Community & Support

License

BioMCP is licensed under the MIT License. See LICENSE for details.