remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Integrations
Enables searching and retrieval of biomedical literature from PubMed/PMC including article search and full text access through the PubTator3 API.
Offers a comprehensive CLI for direct interaction with biomedical databases through Python, allowing users to search for articles, clinical trials, and variants via command line.
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
NOTE: BioMCP is installable via the python package name biomcp-python.
Quick Start Options
For Claude Desktop Users
The easiest way to install BioMCP for Claude Desktop is via Smithery:
This automatically configures the BioMCP MCP server for use with Claude Desktop.
For Python/CLI Users
Install the BioMCP package using pip or uv:
Or preferably using uv for faster installation:
You can also run BioMCP commands directly without installation:
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:
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:
Command Line Interface
BioMCP provides a comprehensive CLI for direct interaction with biomedical
databases. Note, the package name is biomcp-python, not biomcp.
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.
MCP Registries
This server cannot be installed
Provides LLMs with structured access to critical biomedical databases including PubTator3 (PubMed/PMC), ClinicalTrials.gov, and MyVariant.info through the Model Context Protocol.