home / mcp / gnomad mcp server
Model Context Protocol server for gnomAD (Genome Aggregation Database) GraphQL API
Configuration
View docs{
"mcpServers": {
"shukwong-gnomad-mcp-server": {
"command": "node",
"args": [
"/path/to/gnomad-mcp-server/dist/index.js"
]
}
}
}You run an MCP server that exposes gnomAD data through a programmable interface, letting AI assistants query gene constraints, variant frequencies, population data, and other genomic information. This server enables fast, structured access to gnomAD resources so you can build aware, data-driven assistants and workflows without manual data wrangling.
You interact with the gnomAD MCP Server by connecting your MCP client to the local or remote MCP endpoint and issuing requests that target genes, variants, regions, and populations. Use the available tools to search for genes or variants, retrieve detailed gene information including constraint scores, and fetch population-specific allele frequencies. The server supports region queries, transcript data, structural variants, and mitochondrial variants, allowing you to build rich genetic data queries into your AI workflows.
Prerequisites: you need Node.js 18 or higher and npm or yarn installed on your system.
Step 1. Clone the project repository.
Step 2. Install dependencies.
Step 3. Build the server.
Run the server locally using the standard runtime command shown for development and testing.
Configuration is provided to connect the server with clients via local stdio execution. You can also start the server through MCP CLI for convenience.
Search for genes, variants, or regions in gnomAD with options for reference genome and dataset.
Fetch detailed information about a gene, including constraint scores and related metadata.
Retrieve detailed information about a specific variant, including population frequencies and annotations.