`transcript`

Pack: gnomad · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/transcript for the schema, then POST the same URL with its arguments for the data.

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.

Parameters

Name	Type	Required	Description
`transcript_id`	string	yes	Ensembl transcript id (ENST…)
`dataset`	string	no

Example call

Arguments

{
  "transcript_id": "ENST00000357144"
}

curl

curl -X POST https://gateway.pipeworx.io/gnomad/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"transcript","arguments":{"transcript_id":"ENST00000357144"}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('transcript', {
  "transcript_id": "ENST00000357144"
});

More examples

{
  "transcript_id": "ENST00000380152",
  "dataset": "gnomad_r4"
}

Response shape

Field	Type	Description
`transcript`	object
`truncated`	boolean	True when this response holds fewer variants than gnomAD has (see variants_page)
`variants_page`	object	How the variant list was paged. gnomAD returns every variant with no limit of its own, so the pack pages it; total is exact.

Full JSON Schema

{
  "type": "object",
  "properties": {
    "transcript": {
      "type": "object",
      "properties": {
        "transcript_id": {
          "type": "string",
          "description": "Ensembl transcript ID"
        },
        "gene_symbol": {
          "type": "string",
          "description": "Gene symbol"
        },
        "chrom": {
          "type": "string",
          "description": "Chromosome"
        },
        "start": {
          "type": "number",
          "description": "Transcript start position"
        },
        "stop": {
          "type": "number",
          "description": "Transcript stop position"
        },
        "variants": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "variant_id": {
                "type": "string",
                "description": "Variant identifier"
              },
              "consequence": {
                "type": "string",
                "description": "VEP consequence"
              },
              "exome": {
                "type": "object",
                "properties": {
                  "af": {
                    "type": "number",
                    "description": "Allele frequency"
                  }
                }
              },
              "genome": {
                "type": "object",
                "properties": {
                  "af": {
                    "type": "number",
                    "description": "Allele frequency"
                  }
                }
              }
            }
          }
        }
      }
    },
    "truncated": {
      "type": "boolean",
      "description": "True when this response holds fewer variants than gnomAD has (see variants_page)"
    },
    "variants_page": {
      "type": "object",
      "description": "How the variant list was paged. gnomAD returns every variant with no limit of its own, so the pack pages it; total is exact.",
      "properties": {
        "total": {
          "type": "number",
          "description": "Variants gnomAD holds for this query"
        },
        "returned": {
          "type": "number",
          "description": "Variants in this response"
        },
        "offset": {
          "type": "number",
          "description": "Variants skipped before this page"
        },
        "limit": {
          "type": "number",
          "description": "Page size applied"
        },
        "next_offset": {
          "type": [
            "number",
            "null"
          ],
          "description": "Offset for the next page, null on the last page"
        },
        "upstream_bytes": {
          "type": "number",
          "description": "Size of the full upstream response, in bytes"
        },
        "note": {
          "type": "string",
          "description": "Plain-language statement of what is and is not in this page"
        }
      }
    }
  }
}

Connect

Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://pipeworx.io/mcp"
    }
  }
}

Connect to just the gnomad pack

{
  "mcpServers": {
    "gnomad": {
      "url": "https://gateway.pipeworx.io/gnomad/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

transcript