@cyanheads/gnomad-genetics-mcp-server

Tools

Five gnomAD tools, plus three for SQL analytics over the DuckDB-backed canvas tables the list tools materialize:

gnomad_get_variant

The "how common, is it benign" answer in one call.

• Batch up to 25 IDs per call, each a chrom-pos-ref-alt variantId (e.g. 1-55051215-G-GA) or an rsID (e.g. rs11591147)

• Per-item partial success — a malformed or absent ID lands in failed[] without failing the others

• Per-ancestry frequency vector is returned in full, never collapsed to a single global AF

• Reports which callset(s) (exome / genome) carry the variant, quality flags, transcript consequence, in-silico predictor scores, and the ClinVar significance gnomAD joins per variant

• An empty found[] for a well-formed ID means the variant is not in the chosen dataset — pair with gnomad_get_coverage to confirm the position is callable before concluding true absence

gnomad_get_gene_constraint

The orthogonal axis to allele frequency — a loss-of-function variant matters far more in a gene intolerant to being broken.

• Accepts an HGNC symbol (PCSK9) or an Ensembl gene ID (ENSG00000169174)

• Returns pLI (>0.9 intolerant), LOEUF / oe_lof_upper (<0.6 intolerant in v4, <0.35 in v2) with its lower bound, observed/expected ratios for LoF / missense / synonymous, and the three Z-scores

• Many genes have null constraint (sparse upstream) — null fields are reported as such, never fabricated

• constraint_flags surfaces v4 beta caveats flagged by the gnomAD team

gnomad_list_gene_variants

List variants across a gene, transcript, or region, then SQL the full set.

• Supply exactly one of gene, transcript_id, or region (chrom-start-stop, 1-based inclusive)

• Optional filters: one consequence_class (lof / missense / synonymous / other) and/or a maximum allele frequency

• The full result is staged on a DataCanvas table named gene_variants with an inline preview returned alongside canvas_id and table_name — query it with gnomad_dataframe_query to rank by AF, count by consequence, or group across the complete set

• Reusing a canvas_id REPLACES the staged table; it does not append

• When the canvas is disabled (CANVAS_PROVIDER_TYPE != duckdb) the tool returns a capped inline preview with spilled=false and the SQL path is unavailable

gnomad_get_coverage

Disambiguate a true absent variant from an uncallable position.

• Supply exactly one of gene, transcript_id, or region

• Returns mean and median read depth plus the mean fraction of samples covered at each threshold (1× through 100×), summarized per callset track

• coverage_source narrows to one track (exome / genome); omit to return every available track

• A variant missing from a well-covered region is informative; one missing from a poorly-covered region is not

gnomad_search_clinvar

Gene-panel curation depth beyond the per-variant ClinVar join, via NCBI E-utilities.

• Returns a gene's classified ClinVar variants — clinical significance, review status with a 0–4 star rating, associated conditions, molecular consequences, and submission counts

• Optional filters: clinical_significance (e.g. pathogenic) and a minimum star rating (min_review_stars, 0–4)

• The full set is staged on the clinvar_variants canvas table with an inline preview; reusing a canvas_id REPLACES that table

• Keyless, but honors NCBI_API_KEY for a higher rate limit (10 vs 3 req/s)

Canvas dataframe tools

gnomad_dataframe_query, gnomad_dataframe_describe, and gnomad_dataframe_drop operate on the canvas tables the list tools stage.

• gnomad_dataframe_query runs single-statement SELECTs only — writes, DDL, and file/HTTP table functions are rejected by the canvas gate

• gnomad_dataframe_describe returns each staged table's name, row count, and column schema — call it before writing SQL

• gnomad_dataframe_drop is a deliberate mutation (readOnlyHint: false); it stays absent from tools/list unless GNOMAD_DATAFRAME_DROP_ENABLED=true

• All three require CANVAS_PROVIDER_TYPE=duckdb; without it they return a canvas_disabled error

Related MCP server: EVEE MCP Server

Resources and prompts

All resource data is also reachable via tools. The list tools (gnomad_list_gene_variants, gnomad_get_coverage, gnomad_search_clinvar) return analytical row sets rather than stable single-URI documents, so they are not exposed as resources — call the tools instead.

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool, resource, and prompt definitions — single file per primitive, framework handles registration and validation

• Unified error handling — handlers throw, framework catches, classifies, and formats

• Typed error contracts with agent-facing recovery hints

• Pluggable auth: none, jwt, oauth

• Structured logging with optional OpenTelemetry tracing

• STDIO and Streamable HTTP transports

gnomAD-specific:

• Single keyless GraphQL source for the entire core surface — ClinVar significance is joined per variant inside gnomAD's own response

• dataset and reference_genome are distinct, coherence-validated parameters (v4/v3 ⇒ GRCh38, v2.1/ExAC ⇒ GRCh37); both are echoed in every tool's output so a wrong-build coordinate mismatch is visible

• Polite client — conservative concurrency cap and exponential backoff against a community-funded, rate-limited API

• In-conversation SQL analytics: gnomad_list_gene_variants and gnomad_search_clinvar stage their full result on a DuckDB-backed canvas table queryable via gnomad_dataframe_query

Agent-friendly output:

• Per-ancestry allele-frequency vector returned in full, never collapsed to a single global AF — the cross-ancestry contrast is the signal clinical interpretation needs

• Graceful partial failure — gnomad_get_variant returns per-item failed[] rows with actionable messages instead of failing the whole batch

• Provenance on every response — effective dataset and reference_genome echoed back; null upstream fields preserved as null, never fabricated

• Recovery hints on errors (incoherent_build, invalid_target, gene_not_found, canvas_disabled) so callers know the next move

Getting started

Add the following to your MCP client configuration file. gnomAD is a free, keyless API — no credentials required.

{
  "mcpServers": {
    "gnomad-genetics-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/gnomad-genetics-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "gnomad-genetics-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/gnomad-genetics-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "gnomad-genetics-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/gnomad-genetics-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

To enable the SQL analytics path, also set CANVAS_PROVIDER_TYPE=duckdb (requires the @duckdb/node-api peer dependency; unavailable on Cloudflare Workers).

Prerequisites

• Bun v1.3.0 or higher (or Node.js v24+).

• No API key — gnomAD's GraphQL endpoint is keyless. An optional NCBI_API_KEY raises the gnomad_search_clinvar rate limit.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/gnomad-genetics-mcp-server.git

2. Navigate into the directory:

cd gnomad-genetics-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# all vars are optional — the server runs keyless out of the box

Configuration

All variables are optional; the server runs keyless with the defaults below.

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec

Docker

docker build -t gnomad-genetics-mcp-server .
docker run --rm -e MCP_TRANSPORT_TYPE=http -p 3010:3010 gnomad-genetics-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/gnomad-genetics-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md/AGENTS.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic

• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage

• Register new tools and resources in the createApp() arrays in src/index.ts

• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.

gnomAD data is provided by the Genome Aggregation Database (Broad Institute). ClinVar data is provided by NCBI.