MARRVEL-MCP
An MCP server for MARRVEL that enables AI agents to access genetics databases and variant analysis tools for rare disease research.
README
MARRVEL-MCP
<!-- mcp-name: io.github.hyunhwan-bcm/marrvel-mcp -->
A Model Context Protocol (MCP) server for MARRVEL - enabling AI agents to access genetics databases and variant analysis tools for rare disease research.
Demo
Try out MARRVEL-MCP in action:
- <a href="https://chat.marrvel.org">MARRVEL-MCP Chatbot Demo</a>
Quick Start
Installation
git clone https://github.com/hyunhwan-bcm/MARRVEL_MCP.git
cd MARRVEL_MCP
# Using uv (recommended)
uv sync # core MCP server only
uv sync --extra eval # include evaluation framework dependencies
# Or using pip
pip install . # core MCP server only
pip install ".[eval]" # include evaluation framework dependencies
MCP Server Setup
To use MARRVEL-MCP with Claude Desktop, LM Studio, or other MCP-compatible clients, add the following to your client's MCP configuration:
{
"mcpServers": {
"marrvel-mcp": {
"command": "/path/to/your/.venv/bin/python",
"args": ["/path/to/MARRVEL_MCP/server.py"]
}
}
}
Replace the paths with the actual locations of your Python virtual environment and the cloned repository.
Usage
Ask your AI assistant natural language questions about genes, variants, diseases, orthologs, and literature. For example test cases, see mcp_llm_test/test_cases.yaml.
Features
MARRVEL-MCP provides 35+ MCP tools for genetics research:
- Gene queries - by symbol, Entrez ID, or genomic position
- Variant analysis - dbNSFP, ClinVar, gnomAD, DGV, Geno2MP
- Disease associations - OMIM, HPO, DECIPHER
- Ortholog information - DIOPT across model organisms
- Expression data - GTEx, Pharos drug targets, STRING interactions
- Literature search - PubMed, PMC full text/tables/figures
- Coordinate conversion - hg19/hg38 liftover
See docs/TOOL_RELATIONSHIPS.md for a visual diagram of tool chains and workflows.
Documentation
| Document | Description |
|---|---|
mcp_llm_test/README.md |
Evaluation framework for benchmarking LLMs with MARRVEL-MCP |
docs/TOOL_RELATIONSHIPS.md |
Tool relationship graph and common analysis chains |
marrvel_mcp/README.md |
Package API reference for the marrvel_mcp module |
tests/README.md |
Test suite overview and instructions |
Development
# Install with dev dependencies
uv sync --group dev --extra eval
# Run tests
pytest tests/
# Format code
black .
Citation
Wang J, et al. (2017) MARRVEL: Integration of Human and Model Organism Genetic Resources to Facilitate Functional Annotation of the Human Genome. Am J Hum Genet 100(6):843-853.
Support
- Website: https://marrvel.org
- API Docs: https://marrvel.org/doc
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.