Opengenes MCP

🚀 opengenes-mcp

The MCP (Model Context Protocol) server for OpenGenes database, offering a standardized interface to access aging and longevity research data. It automatically fetches the latest data, ensuring you always have the most up - to - date information.

🚀 Quick Start

Installing uv

# Download and install uv
curl -LsSf https://astral.sh/uv/install.sh | sh

# Verify installation
uv --version
uvx --version

uvx is a very nice tool that can run a python package installing it if needed.

Running with uvx

You can run the opengenes-mcp server directly using uvx without cloning the repository:

# Run the server in streamed http mode (default)
uvx opengenes-mcp

# Or explicitly specify stdio mode
uvx opengenes-mcp stdio

# Run the server in streamable HTTP mode on default (3001) port
uvx opengenes-mcp server

# Run on a specific port
uvx opengenes-mcp server --port 8000

# Run the server in SSE mode
uvx opengenes-mcp sse

Note: Currently, we do not have a Swagger/OpenAPI interface, so accessing the server directly in your browser will not show much useful information. To explore the available tools and capabilities, you should either use the MCP Inspector (see below) or connect through an MCP client to see the available tools.

✨ Features

• Structured Access: Direct connection to authoritative aging and longevity research data.
• Natural Language Queries: Simplified interaction with specialized databases through SQL.
• Type Safety: Strong typing and validation through FastMCP.
• AI Integration: Seamless integration with AI assistants and agents.
• Automatic Data Updates: Automatically downloads the latest OpenGenes database from Hugging Face Hub, ensuring you always have access to the most up - to - date data.
• Safety Features: Read - only access, input validation, and comprehensive error handling.

📦 Installation

The OpenGenes MCP server can be set up in multiple ways:

Repository setup

# Clone the repository
git clone https://github.com/longevity-genie/opengenes-mcp.git
cd opengenes-mcp
uv sync

Running the MCP Server

If you already cloned the repo you can run the server with uv:

# Start the MCP server locally (HTTP mode)
uv run server

# Or start in STDIO mode  
uv run stdio

# Or start in SSE mode
uv run sse

💻 Usage Examples

Basic Usage

Here's how the OpenGenes MCP server works in practice with AI assistants: Example showing how to query the OpenGenes database through an AI assistant using natural language, which gets translated to SQL queries via the MCP server. You can use this database both in chat interfaces for research questions and in AI - based development tools (like Cursor, Windsurf, VS Code with Copilot) to significantly improve your bioinformatics productivity by having direct access to aging and longevity research data while coding.

Advanced Usage

The server provides three main tools for interacting with the OpenGenes database:

1. opengenes_db_query(sql: str): Execute read - only SQL queries against the OpenGenes database.
2. opengenes_get_schema_info(): Get detailed schema information including tables, columns, and enumerations.
3. opengenes_example_queries(): Get a list of example SQL queries with descriptions.

📚 Documentation

Data Source and Updates

The OpenGenes MCP server automatically downloads data from the longevity-genie/bio-mcp-data repository on Hugging Face Hub. This ensures:

• Always Up - to - Date: Automatic access to the latest OpenGenes database without manual updates.
• Reliable Distribution: Centralized data hosting with version control and change tracking.
• Efficient Caching: Downloaded files are cached locally to minimize network requests.
• Fallback Support: Local fallback files are supported for development and offline use. The data files are stored in the opengenes subfolder of the Hugging Face repository and include:
• open_genes.sqlite - The complete OpenGenes database.
• prompt.txt - Database schema documentation and usage guidelines.

Configuring your AI Client (Anthropic Claude Desktop, Cursor, Windsurf, etc.)

We provide preconfigured JSON files for different use cases:

• For STDIO mode (recommended): Use mcp-config-stdio.json.
• For HTTP mode: Use mcp-config.json.
• For local development: Use mcp-config-stdio-debug.json.

Configuration Video Tutorial

For a visual guide on how to configure MCP servers with AI clients, check out our configuration tutorial video for our sister MCP server (biothings-mcp). The configuration principles are exactly the same for the OpenGenes MCP server - just use the appropriate JSON configuration files provided above.

Inspecting OpenGenes MCP server

npx @modelcontextprotocol/inspector --config mcp-config-stdio.json --server opengenes-mcp

npx @modelcontextprotocol/inspector --config mcp-config.json --server opengenes-mcp

npx @modelcontextprotocol/inspector --config mcp-config-stdio-debug.json --server opengenes-mcp

npx @modelcontextprotocol/inspector

Integration with AI Systems

Simply point your AI client (like Cursor, Windsurf, ClaudeDesktop, VS Code with Copilot, or others) to use the appropriate configuration file from the repository.

Database Schema

Example Queries

-- Get top genes with most lifespan experiments
SELECT HGNC, COUNT(*) as experiment_count 
FROM lifespan_change 
WHERE HGNC IS NOT NULL 
GROUP BY HGNC 
ORDER BY experiment_count DESC 
LIMIT 10;

-- Find genes that increase lifespan in mice
SELECT DISTINCT HGNC, effect_on_lifespan 
FROM lifespan_change 
WHERE model_organism = 'mouse' 
AND effect_on_lifespan = 'increases lifespan' 
AND HGNC IS NOT NULL;

-- Get hallmarks of aging for genes
SELECT HGNC, "hallmarks of aging" 
FROM gene_hallmarks 
WHERE "hallmarks of aging" LIKE '%mitochondrial%';

-- Find longevity associations by ethnicity
SELECT HGNC, "polymorphism type", "nucleotide substitution", ethnicity 
FROM longevity_associations 
WHERE ethnicity LIKE '%Italian%';

-- Find genes with both lifespan effects and longevity associations
SELECT DISTINCT lc.HGNC 
FROM lifespan_change lc 
INNER JOIN longevity_associations la ON lc.HGNC = la.HGNC 
WHERE lc.HGNC IS NOT NULL;

🔧 Technical Details

Safety Features

• Read - only access: Only SELECT queries are allowed.
• Input validation: Blocks INSERT, UPDATE, DELETE, DROP, CREATE, ALTER, TRUNCATE operations.
• Error handling: Comprehensive error handling with informative messages.

Testing & Verification

The MCP server is provided with comprehensive tests including LLM - as - a - judge tests that evaluate the quality of responses to complex queries. However, LLM - based tests are disabled by default in CI to save costs.

Environment Setup for LLM Agent Tests

If you want to run LLM agent tests that use MCP functions with Gemini models, you need to set up a .env file with your Gemini API key:

# Create a .env file in the project root
echo "GEMINI_API_KEY=your-gemini-api-key-here" > .env

Note: The .env file and Gemini API key are only required for running LLM agent tests. All other tests and basic MCP server functionality work without any API keys.

Running Tests

Run tests for the MCP server:

uv run pytest -vvv -s

You can also run manual tests:

uv run python test/manual_test_questions.py

You can use MCP inspector with locally built MCP server same way as with uvx.

Note: Using the MCP Inspector is optional. Most MCP clients (like Cursor, Windsurf, etc.) will automatically display the available tools from this server once configured. However, the Inspector can be useful for detailed testing and exploration.

If you choose to use the Inspector via npx, ensure you have Node.js and npm installed. Using nvm (Node Version Manager) is recommended for managing Node.js versions.

Example questions that MCP helps to answer

📄 License

This project is licensed under the MIT License.

Acknowledgments

• OpenGenes Database for the comprehensive aging research data.
  • Rafikova E, Nemirovich - Danchenko N, Ogmen A, Parfenenkova A, Velikanova A, Tikhonov S, Peshkin L, Rafikov K, Spiridonova O, Belova Y, Glinin T, Egorova A, Batin M. Open Genes - a new comprehensive database of human genes associated with aging and longevity. Nucleic Acids Res. 2024 Jan 5;52(D1):D950 - D962. doi: 10.1093/nar/gkad712. PMID: 37665017; PMCID: PMC10768108.
• Model Context Protocol for the protocol specification.
• FastMCP for the MCP server framework.

This project is part of the Longevity Genie organization, which develops open - source AI assistants and libraries for health, genetics, and longevity research.

Other MCP Servers by Longevity Genie

We also develop other specialized MCP servers for biomedical research:

• biothings-mcp - MCP server for BioThings.io APIs, providing access to gene annotation (mygene.info), variant annotation (myvariant.info), and chemical compound data (mychem.info)

We are supported by:

HEALES - Healthy Life Extension Society

and

IBIMA - Institute for Biostatistics and Informatics in Medicine and Ageing Research

Contributing

We welcome contributions from the community! 🎉 Whether you're a researcher, developer, or enthusiast interested in aging and longevity research, there are many ways to get involved:

We especially encourage you to try our MCP server and share your feedback with us! Your experience using the server, any issues you encounter, and suggestions for improvement are incredibly valuable for making this tool better for the entire research community.

Ways to Contribute

• 🐛 Bug Reports: Found an issue? Please open a GitHub issue with detailed information.
• 💡 Feature Requests: Have ideas for new functionality? We'd love to hear them!
• 📝 Documentation: Help improve our documentation, examples, or tutorials.
• 🧪 Testing: Add test cases, especially for edge cases or new query patterns.
• 🔍 Data Quality: Help identify and report data inconsistencies or suggest improvements.
• 🚀 Performance: Optimize queries, improve caching, or enhance server performance.
• 🌐 Integration: Create examples for new MCP clients or AI systems.
• 🎥 Tutorials & Videos: Create tutorials, video guides, or educational content showing how to use MCP servers.
• 📖 User Stories: Share your research workflows and success stories using our MCP servers.
• 🤝 Community Outreach: Help us evangelize MCP adoption in the bioinformatics community.

Tutorials, videos, and user stories are especially valuable to us! We're working to push the bioinformatics community toward AI adoption, and real - world examples of how researchers use our MCP servers (this one and others we develop) help demonstrate the practical benefits and encourage wider adoption.

Getting Started

1. Fork the repository.
2. Create a feature branch (git checkout -b feature/amazing-feature).
3. Make your changes and add tests.
4. Run the test suite (uv run pytest).
5. Commit your changes (git commit -m 'Add amazing feature').
6. Push to your branch (git push origin feature/amazing-feature).
7. Open a Pull Request.

Development Guidelines

• Follow the existing code style (we use black for formatting).
• Add tests for new functionality.
• Update documentation as needed.
• Keep commits focused and write clear commit messages.

Questions or Ideas?

Don't hesitate to open an issue for discussion! We're friendly and always happy to help newcomers get started. Your contributions help advance open science and longevity research for everyone. 🧬✨

Known Issues

Database Coverage

Currently, this MCP server uses only a subset of the complete OpenGenes database. The full OpenGenes database contains additional tables and data that are not yet included in our MCP implementation. We need contributors to help extend support for the complete database! If you're interested in helping expand the database coverage, please see our Contributing section.

Test Coverage

While we provide comprehensive tests including LLM - as - a - judge evaluations, not all test cases have been manually verified against the actual OpenGenes web interface. Some automated test results may need manual validation to ensure accuracy. Contributions to improve test coverage and validation are welcome.