Omics AI MCP Server

A Model Context Protocol (MCP) server that enables AI agents to conversationally interact with Omics AI Explorer networks for genomics research and data analysis.

This MCP server wraps the functionality of theomics-ai-python-libraryto provide AI agents with seamless access to genomics data across multiple Omics AI Explorer networks including:

git clone https://github.com/mfiume/omics-ai-mcp.git cd omics-ai-mcp npm install

{ "mcpServers": { "omics-ai": { "command": "node", "args": ["src/index.js"], "cwd": "/path/to/omics-ai-mcp" } } }

Once configured, AI agents can conversationally query genomics data:

Agent: "What collections are available on the Viral AI network?"

User: "Show me the tables in the virusseq collection"

Agent: "List the first 10 variants from the variants table where chromosome equals chr1"

User: "How many total variants are in the VirusSeq database?"

Lists all available collections in a network.

- network(required): Network name (hifisolves, viral, neuroscience, etc.) or full URL
- access_token(optional): Authentication token

Lists all tables in a specific collection.

- network(required): Network name or URL
- collection_slug(required): Collection identifier (e.g., "virusseq", "gnomad")
- access_token(optional): Authentication token

Retrieves the schema and field definitions for a table.

- network(required): Network name or URL
- collection_slug(required): Collection identifier
- table_name(required): Qualified table name (e.g., "collections.virusseq.variants")
- access_token(optional): Authentication token

Queries data from a table with optional filtering and pagination.

- network(required): Network name or URL
- collection_slug(required): Collection identifier
- table_name(required): Qualified table name
- filters(optional): Filter criteria object
- limit(optional): Max rows to return (default: 100)
- offset(optional): Rows to skip (default: 0)
- order_by(optional): Sort specification
- access_token(optional): Authentication token

- network(required): Network name or URL
- collection_slug(required): Collection identifier
- table_name(required): Qualified table name
- filters(optional): Filter criteria object
- access_token(optional): Authentication token

Executes direct SQL queries against a collection using Trino syntax with enhanced result formatting.

- network(required): Network name or URL
- collection_slug(required): Collection identifier
- sql(required): SQL query string (use Trino syntax with double quotes for identifiers)
- max_polls(optional): Maximum number of polling attempts (default: 10)
- poll_interval(optional): Seconds to wait between polls (default: 2.0)
- access_token(optional): Authentication token

- Automatic async query polling with robust error handling
- Intelligent result formatting (table view for simple data, JSON for complex)
- Progress indicators and pagination info
- Timeout management for long-running queries

- SELECT COUNT() FROM "schema"."table"
- SELECT FROM "schema"."variants" WHERE chrom = 'chr1' LIMIT 10
- SELECT DISTINCT chrom FROM "schema"."variants" ORDER BY chrom

The server supports these pre-configured networks (use short names for convenience):

The server includes robust error handling for:

- Network connectivity issues
- Authentication failures
- Invalid parameters
- API response parsing errors
- Timeout handling for long-running queries

# Development mode with auto-restart npm run dev # Production mode npm start

MIT License - see LICENSE file for details.

- omics-ai-python-library- Python client library
- Model Context Protocol- MCP specification and SDKs

Interact with DROMA drug-omics association analysis databases using natural language.