
BioMCP
Provides LLMs with structured access to critical biomedical databases including PubTator3 (PubMed/PMC), ClinicalTrials.gov, and MyVariant.info through the Model Context Protocol.
README
BioMCP: Biomedical Model Context Protocol
BioMCP is an open source (MIT License) toolkit for biomedical research AI assistants and agents. Built following the Model Context Protocol (MCP), it supports searching and retrieving clinical trials, pubmed articles, and genomic variants.
Tools
- PubTator3 (PubMed/PMC)
- Article Search
- Full Text
- ClinicalTrials.gov
- Clinical Trial Advanced Search
- Protocols
- Outcomes
- Locations
- Reference
- MyVariant.info
- Variant Search
- Annotations (CIViC, ClinVar, COSMIC, dbSNP, etc.)
Installation
Quick Start Options
For Claude Desktop Users
The easiest way to install BioMCP for Claude Desktop is via Smithery:
npx -y @smithery/cli install @genomoncology/biomcp --client claude
This automatically configures the BioMCP MCP server for use with Claude Desktop.
For Python/CLI Users
Install the BioMCP package using pip or uv:
pip install biomcp-python
Or preferably using uv for faster installation:
uv pip install biomcp-python
You can also run BioMCP commands directly without installation:
uvx --from biomcp-python biomcp trial search --condition "lung cancer" --intervention "pembro"
Advanced Installation
Manual Claude Desktop Integration
To manually configure BioMCP as an MCP Server for Claude Desktop:
- Open Claude Desktop settings
- Navigate to the MCP Servers configuration section
- Add the following configuration:
{
"globalShortcut": "",
"mcpServers": {
"biomcp": {
"command": "uv",
"args": ["run", "--from", "biomcp-python", "biomcp", "run"]
}
}
}
Note: If you get a SPAWN ENOENT
warning, make sure your uv
executable
is in your PATH or provide a full path to it (e.g. /Users/name/.local/bin/uv).
Verification
To verify your BioMCP MCP Server installation, use the MCP Inspector: Server, using the MCP Inspector, run the following command:
npx @modelcontextprotocol/inspector uv run biomcp run
Command Line Interface
BioMCP provides a comprehensive CLI for direct interaction with biomedical databases:
# Get help
biomcp --help
# Run the MCP server
biomcp run
# Search for articles
biomcp article search --gene BRAF --disease Melanoma
# Get article details by PMID
biomcp article get 21717063 --full
# Search for clinical trials
biomcp trial search --condition "Lung Cancer" --phase Phase_3
# Get trial details by NCT ID
biomcp trial get NCT04280705 Protocol
# Search for variants
biomcp variant search --gene BRAF --significance Pathogenic
# Get variant details
biomcp variant get rs113488022
Commercial Version: OncoMCP
OncoMCP extends BioMCP with GenomOncology's enterprise-grade precision oncology platform (POP), providing healthcare organizations with:
- On-premise deployment with full HIPAA compliance
- Real-time clinical trial recruiting status and arm-level matching
- Seamless EHR and clinical data warehouse integration
- Curated knowledge base of 15,000+ clinical trials and FDA approvals
- Patient-trial matching using integrated clinical and molecular profiles
- Advanced NLP for structured data extraction and normalization
- Comprehensive biomarker and mutation rule processing
Find out more about GenomOncology and OncoMCP by visiting: GenomOncology.
License
This project is licensed under the MIT License.
Sources
BioMCP integrates data from several authoritative biomedical databases, each with their own terms of service and data usage policies. Users should be aware of these policies when utilizing BioMCP for various applications.
PubTator3 / PubMed
- Provider: National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM)
- Content: Biomedical literature indexed in PubMed and PubMed Central
- Terms of Service: NCBI/NLM Terms and Conditions
- Access Limits: Standard access is limited to a specific number of requests per second. Higher throughput available with an API key.
- Citation Requirements: Publications using data from PubMed should cite the appropriate NCBI/NLM resources.
- Underlying Sources: Articles from thousands of biomedical journals and repositories.
ClinicalTrials.gov
- Provider: National Library of Medicine (NLM)
- Content: Clinical trials registry and results database
- Terms of Service: ClinicalTrials.gov Terms and Conditions
- Data Usage: Data is freely available for research and academic purposes. Commercial use may have additional restrictions.
- API Access: ClinicalTrials.gov API
- Citation Requirements: Any publication using data from ClinicalTrials.gov should properly acknowledge the source.
MyVariant.info
- Provider: The Su Lab at Scripps Research
- Content: Comprehensive genetic variant annotation compiled from multiple databases
- Terms of Service: MyVariant.info Terms of Service
- Annotation Sources: Comprehensive list of annotation sources
- Attribution: Users should properly attribute both MyVariant.info and the original annotation sources in publications.
- Primary Data Sources Include:
- ClinVar: Clinical interpretations of genetic variants
- COSMIC: Catalogue of Somatic Mutations in Cancer
- dbSNP: Database of single nucleotide polymorphisms
- CIViC: Clinical Interpretations of Variants in Cancer
- gnomAD: Genome Aggregation Database
- CADD: Combined Annotation Dependent Depletion scores
Important Usage Notes
When using BioMCP, please be aware that:
- Attribution Requirements: Publications or applications using data obtained through BioMCP should cite both BioMCP and the original data sources appropriately.
- Data Currency: Information retrieved may not represent the most current data available from the original sources due to update frequencies.
- Usage Restrictions: While BioMCP provides access to these resources, users must comply with the individual terms of service for each data source, particularly for commercial applications.
- Protected Health Information: BioMCP does not handle or provide access to protected health information (PHI) or personally identifiable information (PII).
For additional information about specific data sources or usage policies, please refer to the documentation provided by each source database.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.