MCP server exposing 3 tools for myvariant.
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/myvariant/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}query — 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.variant — Get the full merged annotation for a single human genetic variant by its HGVS id (e.g. "chr7:g.140453136A>T"). COORDINATES ARE hg19/GRCh37 BY DEFAULT — pass assembly "hg38" for GRCh38 positions, which is what gnomAD and Ensembl hand you. Returns annotations aggregated from dbSNP, ClinVar (pathogenicity / clinical significance), CADD and dbNSFP (deleteriousness/conservation scores), and gnomAD (population allele frequencies). Use to look up a known variant and read its pathogenicity and population frequency.metadata — Returns MyVariant.info build metadata: total indexed variant count, available annotation sources (dbSNP, ClinVar, CADD, dbNSFP, gnomAD), and their current release/build versions.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/myvariant/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io