@pipeworx/gnomad

Connect: https://pipeworx.io/mcp — every tool in the catalog, including @pipeworx/gnomad’s. Install: one-click buttons

No MCP client? Skip the connection: POST https://gateway.pipeworx.io/v1/tools/search_packs {"query":"..."} to find a tool below, GET /v1/tools/<name> for its schema, POST the same URL with arguments for the data — see For AI agents.

Tools: 5

gnomAD MCP — Genome Aggregation Database (Broad Institute) public GraphQL endpoint. Population allele frequencies + variant pathogenicity annotations. Keyless.

Tools

• variant(variant_id, dataset?) — by chr-pos-ref-alt (e.g. 1-55051215-G-A) or rsid
• gene(gene_symbol_or_id, dataset?, limit?, offset?) — variants in / near a gene
• region(chrom, start, stop, assembly, dataset?, limit?, offset?) — variants in a genomic region
• transcript(transcript_id, dataset?, limit?, offset?) — variants in / near a transcript
• search(query) — gene / variant search (autocomplete)

Variant lists are paged

gnomAD returns every variant for a gene, region or transcript with no limit of its own (BRCA1 has about 7,300). gene, region and transcript return one page — limit (default 500, max 2,000) starting at offset (default 0) — and say so in the response:

• truncated: true whenever the page holds fewer variants than gnomAD has;
• variants_page: total (exact), returned, offset, limit, next_offset (null on the last page), upstream_bytes, and a plain note.

To get more, call again with offset = next_offset, raise limit, or narrow the query with region. The page is cut while the response streams in, so a large gene costs the gateway one page of memory, not the whole list.

dataset defaults to gnomad_r4 (most recent release). Other valid: gnomad_r3, gnomad_r2_1, gnomad_sv_r4, etc.

Data source

https://gnomad.broadinstitute.org/api

Tools

• 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
• 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 gues
• 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. V
• 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 partia