allele-registry-mcp-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@allele-registry-mcp-serverresolve HGVS NM_000546.5:c.100G>A to a CA ID"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
allele-registry-mcp-server
MCP server wrapping the ClinGen Allele Registry (https://reg.clinicalgenome.org) — canonical allele identity for genetic variants. Resolves any HGVS / dbSNP / ClinVar / gnomAD reference to a stable ClinGen Allele Registry ID (CA#) and its cross-references, so a variant keeps one identity across genome builds and transcript versions.
Cloudflare Worker built on McpAgent (agents/mcp), REST + Code Mode via @bio-mcp/shared. Read endpoints only; no auth. Dev port 8905.
Why it exists
tmVar3's ~550 GB of chromosome-sharded SQLite exists to turn an HGVS string into a canonical allele. The Allele Registry does the same thing over a free public REST API — so we wrap the API instead of re-hosting the index. Every allele_registry_execute result carries a verifiable _meta.citation, and a CA# is a content-addressed allele identifier that drops straight into the fleet's attestation story.
Related MCP server: OpenCRAVAT
Tools (Code Mode)
allele_registry_search— discover endpoints in the curated catalogallele_registry_execute— run JS against the API in a V8 isolate (api.get/api.post,searchSpec, no network/keys); results carry_meta.citationallele_registry_get_schema/allele_registry_query_data— inspect + SQL-query staged results
Develop
./scripts/dev-servers.sh allele-registry # wrangler dev on :8905
pnpm --filter allele-registry-mcp-server run testUpstream
Base:
https://reg.clinicalgenome.org—GET /allele?hgvs=…,GET /allele/{CAid}, resolution by dbSNP / ClinVar / gnomAD / MyVariantInfo.Source descriptor:
ClinGen Allele Registry(ClinGen / NIH, freely available).
This server cannot be deployed
Maintenance
Related MCP Connectors
Broad Institute gnomAD genomic variant database (GraphQL)
Look up allele frequencies by ancestry, gene constraint, variants, and coverage over gnomAD.
MCP gateway federating 22 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.
Search and resolve Naturepedia, Robbie's Razor, and GC-MRD-v2.0 canonical resources.
Related MCP Servers
- AlicenseBqualityDmaintenanceProvides a programmatic interface to the Genome Aggregation Database (gnomAD) API across versions v2.1.1, v3.1.2, and v4.1.0. It enables users to query gene metadata, variant information, population frequencies, and ClinVar data through a unified schema.126Apache 2.0

OpenCRAVATofficial
FlicenseNot gradedqualityCmaintenanceAnnotate variants by with a deep and rich set of data. Can annotate: genetic change, rsID, CAid, HGVS (g./c./p.), protein change.5-- FlicenseAqualityFmaintenanceProvides interpretable variant effect predictions for 4.2 million ClinVar variants using the EVEE API. Enables searching, comparing, and analyzing genetic variants with AI-generated mechanistic interpretations and disruption profiles.617-
- AlicenseNot gradedqualityAmaintenanceEnables querying ClinGen curated evidence for gene-disease validity, dosage, actionability, and variant pathogenicity via MCP tools.MIT