This server wraps the Broad Institute's gnomAD database, exposing five GraphQL backed tools for querying genomic variant data. You get variant lookups by coordinates or rsID, gene queries with variant lists, region scans up to 25kb, transcript details, and autocomplete search. It runs through Pipeworx's gateway infrastructure, which means you can either connect directly to gnomAD or use their unified endpoint for 250+ data sources. The ask_pipeworx tool lets you skip manual tool selection and just ask questions in plain English. Useful if you're building genomics workflows in Claude and need quick access to population frequency data, pathogenicity predictions, or variant annotations without standing up your own gnomAD queries.
gnomAD MCP — Broad Institute Genome Aggregation Database (GraphQL).
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
| Tool | Description |
|---|---|
variant | Variant by chr-pos-ref-alt (e.g. "1-55051215-G-A") or rsid. |
gene | Gene info + variants. Accepts gene symbol (e.g. "BRCA1") or Ensembl gene id. |
region | Variants in a genomic region (≤25kb recommended). |
transcript | Transcript + variants. |
search | Gene / variant search (autocomplete). |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"gnomad": {
"url": "https://gateway.pipeworx.io/gnomad/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Gnomad data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
hovecapital/read-only-local-postgres-mcp-server
cocaxcode/database-mcp
io.github.infoinlet-marketplace/mcp-mysql
io.github.cybeleri/database-admin
io.github.yash-0620/postgres-mcp-secured