query
Pack: myvariant · Endpoint: https://gateway.pipeworx.io/myvariant/mcp
Search aggregated human genetic-variant annotations on MyVariant.info. Accepts an rsID (“rs58991260”) or a fielded query (“dbnsfp.genename:CDK2”, “clinvar.rcv.clinical_significance:pathogenic”). A bare HGVS id does NOT match here — look one up with the variant tool instead. Each hit merges dbSNP, ClinVar clinical significance, CADD/dbNSFP deleteriousness scores, and gnomAD population allele frequencies. Returns { total, hits, assembly }; hit._id is the HGVS id you can pass to the variant tool, and its coordinates are in the assembly you asked for — hg19 unless you say otherwise.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
query | string | yes | rsID, HGVS id, or fielded query. e.g. “rs58991260”, “chr1:g.218631822G>A”, “dbnsfp.genename:CDK2”. |
fields | string | no | Comma-separated return fields (default: all). e.g. “dbsnp,clinvar,cadd.phred,gnomad_genome.af”. |
size | number | no | Max hits to return, 1-1000 (default 10). |
assembly | string | no |
Example call
Arguments
{
"query": "rs58991260"
}
curl
curl -X POST https://gateway.pipeworx.io/myvariant/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"query","arguments":{"query":"rs58991260"}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('query', {
"query": "rs58991260"
});
More examples
{
"query": "dbnsfp.genename:CDK2",
"size": 20,
"fields": "dbsnp,clinvar,cadd.phred,gnomad_genome.af"
}
Connect
Add this to your MCP client config, or use one-click install buttons:
{
"mcpServers": {
"myvariant": {
"url": "https://gateway.pipeworx.io/myvariant/mcp"
}
}
}
See Getting Started for client-specific install steps.