gnomad 5 tools

MCP server exposing 5 tools for gnomad.

Endpoint

This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.

POST https://gateway.pipeworx.io/gnomad/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list"}

gnomad_variant — Variant by chr-pos-ref-alt (e.g. "1-55051215-G-A") or rsid (e.g. "rs1801133"). Coordinates must match the dataset's genome build: the default gnomad_r4 is GRCh38, so a GRCh37/hg19 position will not be found — pass dataset "gnomad_r2_1" for GRCh37.
gnomad_gene — Gene info + its variants. Accepts gene symbol (e.g. "BRCA1") or Ensembl gene id. Variants are paged (default 500, max 2,000 per call); variants_page gives the exact total and next_offset.
region — Variants in a genomic region (≤25kb recommended). You MUST say which genome build your start/stop are in via assembly — there is no default, because a position is valid in both builds and a wrong guess returns real variants from the wrong locus rather than an error. Variants are paged (default 500, max 2,000 per call); variants_page gives the exact total and next_offset.
transcript — Fetch gnomAD variant data for an Ensembl transcript (ENST…), returning transcript coordinates, gene symbol, chromosome position, and per-variant allele counts (ac/an) from exome and genome datasets. Variants are paged (default 500, max 2,000 per call); variants_page gives the exact total and next_offset.
gnomad_search — Autocomplete-style search across gnomAD genes and variants by free-text query; returns matching Ensembl gene IDs with symbols, and matching variant IDs (an rsid resolves here). Use to resolve a partial gene name, symbol or rsid before calling gene or variant.

Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/gnomad/

Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io