@cyanheads/gnomad-genetics-mcp-server
by cyanheads
README.md
<div align="center">
<h1>@cyanheads/gnomad-genetics-mcp-server</h1>
<p><b>Ancestry allele frequencies, LoF constraint, variant lists, and coverage from gnomAD, joined with ClinVar clinical significance via MCP. STDIO or Streamable HTTP.</b>
<div>7 Tools (+1 opt-in) • 2 Resources • 1 Prompt</div>
</p>
</div>
<div align="center">
[](./CHANGELOG.md) [](./LICENSE) [](https://github.com/users/cyanheads/packages/container/package/gnomad-genetics-mcp-server) [](https://modelcontextprotocol.io/) [](https://www.npmjs.com/package/@cyanheads/gnomad-genetics-mcp-server) [](https://www.typescriptlang.org/) [](https://bun.sh/)
</div>
<div align="center">
[](https://github.com/cyanheads/gnomad-genetics-mcp-server/releases/latest/download/gnomad-genetics-mcp-server.mcpb) [](https://cursor.com/en/install-mcp?name=gnomad-genetics-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvZ25vbWFkLWdlbmV0aWNzLW1jcC1zZXJ2ZXIiXX0=) [](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22gnomad-genetics-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads%2Fgnomad-genetics-mcp-server%22%5D%7D)
[](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)
</div>
<div align="center">
**Public Hosted Server:** [https://gnomad-genetics.caseyjhand.com/mcp](https://gnomad-genetics.caseyjhand.com/mcp)
</div>
---
## Overview
Population genetics over gnomAD (Broad Institute), with ClinVar clinical significance joined in from NCBI. Look up per-ancestry allele frequencies, gene loss-of-function constraint, gene variant catalogs, and sequencing coverage, then query large result sets with SQL.
### Tools
| Tool | Description |
|:---|:---|
| `gnomad_get_variant` | Full population record for one or more variants — AC/AN/AF overall and per genetic-ancestry group, homozygote/hemizygote counts, quality flags, transcript consequence, in-silico predictors, and joined ClinVar significance. |
| `gnomad_get_gene_constraint` | Gene loss-of-function constraint — pLI, LOEUF (`oe_lof_upper`) with confidence interval, observed/expected ratios, and Z-scores. By HGNC symbol or Ensembl gene ID. |
| `gnomad_list_gene_variants` | Every variant in a gene, transcript, or region with allele frequencies and predicted consequences, filterable by consequence class and max allele frequency. |
| `gnomad_get_coverage` | Sequencing coverage across a gene, transcript, or region — mean/median depth and the fraction of samples over depth thresholds, per callset track. |
| `gnomad_search_clinvar` | Gene-level ClinVar detail via NCBI E-utilities — classified variants, review status, conditions, submission counts, and gnomAD-compatible variant IDs, paged by offset. |
| `gnomad_dataframe_query` | Run a read-only SQL `SELECT` across canvas tables staged by the list tools. |
| `gnomad_dataframe_describe` | List the tables staged on a canvas and their columns before writing SQL. |
| `gnomad_dataframe_drop` | Drop a named table from a canvas to reclaim memory. Opt-in via `GNOMAD_DATAFRAME_DROP_ENABLED=true` — off by default. |
### Resources
| Resource | Description |
|:---|:---|
| `gnomad://variant/{dataset}/{variantId}` | Population record for one variant — mirrors `gnomad_get_variant`. |
| `gnomad://gene/{dataset}/{gene}/constraint` | Gene loss-of-function constraint — mirrors `gnomad_get_gene_constraint`. |
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.
### Prompts
| Prompt | Description |
|:---|:---|
| `gnomad_variant_triage` | Guided rare-disease variant-triage workflow: population frequency → gene constraint → callability check, in order. |
## Capability reference
### `gnomad_get_variant` <sub>tool</sub>
- Up to 25 IDs per call (raise via `GNOMAD_MAX_VARIANT_BATCH`), each a `chrom-pos-ref-alt` variantId on chromosome `1`–`22`, `X`, or `Y` with an optional `chr` prefix (e.g. `1-55051215-G-GA`) or an rsID (e.g. `rs11591147`)
- A bad or absent ID lands in `failed[]` as `{ variant, error, reason, recovery }` without failing the rest; mitochondrial IDs (`M`, `MT`, `chrM`) fail as `mitochondrial_unsupported`, and an ambiguous rsID adds `candidates`
- Returns the full per-ancestry frequency vector, the callset(s) carrying the variant, quality flags, consequence, predictor scores, and ClinVar significance. If ClinVar is unavailable (or the lookup passes 45 s), the record returns with `clinvar: null` and `clinvar_unavailable: true`
- An empty `found[]` means the variant is not in the chosen dataset; check `gnomad_get_coverage` before concluding true absence
---
### `gnomad_get_gene_constraint` <sub>tool</sub>
- Accepts an HGNC symbol (`PCSK9`) or an Ensembl gene ID (`ENSG00000169174`)
- Returns pLI (>0.9 intolerant), LOEUF / `oe_lof_upper` with its lower bound, observed/expected ratios for LoF / missense / synonymous, the three Z-scores, and `constraint_flags` (e.g. `no_exp_lof`, `syn_outlier`)
- `constraint_release` names the release the metrics come from. Many genes have null constraint, reported as null:
| `dataset` | Source | `constraint_release` | LoF-intolerance guidance |
|:--|:--|:--|:--|
| `gnomad_r4` | GRCh38 gnomAD constraint | `gnomAD v4.1.2` | LOEUF < 0.45 |
| `gnomad_r3` | GRCh38 gnomAD constraint (gnomAD publishes no v3 constraint) | `gnomAD v4.1.2` | LOEUF < 0.45 |
| `gnomad_r2_1` | GRCh37 gnomAD constraint | `gnomAD v2.1.1` | LOEUF < 0.35 |
| `exac` | GRCh37 ExAC constraint | `ExAC r0.3` | pLI only |
- On `exac` the ratios and LOEUF are null and `constraint_flags` is empty
---
### `gnomad_list_gene_variants` <sub>tool</sub>
- Supply exactly one of `gene`, `transcript_id`, or `region` (`chrom-start-stop`, 1-based inclusive, chromosome `1`–`22`, `X`, or `Y` with an optional `chr` prefix); a blank `gene` or `transcript_id` counts as omitted
- A region must span less than 2,500,000 bp and hold at most ~30,000 variants, otherwise it fails as `invalid_region` or `region_too_large`; mitochondrial targets fail as `mitochondrial_unsupported`
- Optional filters: one `consequence_class` (`lof` / `missense` / `synonymous` / `other`) and/or a maximum allele frequency
- A result too large to inline is staged on the `gene_variants` canvas table, returned as `canvas_id` and `table_name` beside a preview; inspect it with `gnomad_dataframe_describe` and query it with `gnomad_dataframe_query`. Passing a `canvas_id` always writes `gene_variants` there, replacing the previous table. With the canvas disabled (`CANVAS_PROVIDER_TYPE` != `duckdb`), only the capped preview is returned
---
### `gnomad_get_coverage` <sub>tool</sub>
- Supply exactly one of `gene`, `transcript_id`, or `region` (same `chrom-start-stop` form and 2,500,000 bp limit as `gnomad_list_gene_variants`); a blank `gene` or `transcript_id` counts as omitted. Bad regions fail as `invalid_region` or `region_too_large`, and mitochondrial targets as `mitochondrial_unsupported`
- Returns mean and median read depth plus the mean fraction of samples covered at each threshold (1× through 100×), summarized per callset track, with `bucket_size`, `bucket_count`, and `positions` for each
- `coverage_source` narrows to one track (`exome` / `genome`); omit to return every available track
---
### `gnomad_search_clinvar` <sub>tool</sub>
- Takes an HGNC symbol only (an Ensembl gene ID returns guidance and searches nothing). Optional filters: `clinical_significance` (e.g. `pathogenic`) and `min_review_stars` (0–4)
- Returns clinical significance, review status with a 0–4 star rating, conditions, molecular consequences, submission counts, and gnomAD-compatible identifiers (`canonical_spdi`, `rsids`, `grch38_variant_id`). IDs ClinVar has no summary for are listed in `unavailable_ids`
- Pages up to 500 records per call with `offset` / `limit` (1–500); `total_found`, `truncated`, and `next_offset` say whether more remain. `limit` counts records before the filters, so a window can return fewer rows
- A window too large to inline is staged on the `clinvar_variants` canvas table (query it with `gnomad_dataframe_describe` and `gnomad_dataframe_query`); passing a `canvas_id` always writes it there, replacing the previous table. `NCBI_API_KEY` raises the rate limit from 3 to 10 req/s
---
### `gnomad_dataframe_query` <sub>tool</sub>
- Runs single-statement, read-only SQL `SELECT`s against a table staged by `gnomad_list_gene_variants` or `gnomad_search_clinvar` (`gene_variants` or `clinvar_variants`); writes, DDL, and file/HTTP table functions are rejected
- Pages with `offset` (default 0) and `limit` (default 100, max 500); returns `rows`, `columns`, `total`, `truncated`, and `next_offset` (follow it until `null`). Use an `ORDER BY` on a unique key for stable paging, and filter or aggregate in SQL to get past the `CANVAS_DEFAULT_ROW_LIMIT` cap (10,000 by default)
- A row over the 10,000-character page budget fails with `row_too_large`; without `CANVAS_PROVIDER_TYPE=duckdb` it fails with `canvas_disabled`
---
### `gnomad_dataframe_describe` <sub>tool</sub>
- Lists every table staged on a canvas with its row count and column schema (name and DuckDB type)
- Call it before writing SQL for `gnomad_dataframe_query`
- Requires `CANVAS_PROVIDER_TYPE=duckdb` — otherwise fails with a `canvas_disabled` error
---
### `gnomad_dataframe_drop` <sub>tool</sub>
- Drops a named table from a canvas to reclaim memory (`destructiveHint: true`)
- Opt-in via `GNOMAD_DATAFRAME_DROP_ENABLED=true`; absent from `tools/list` when off
- An unknown or expired `canvas_id` fails as `canvas_not_found`; without `CANVAS_PROVIDER_TYPE=duckdb` it fails with `canvas_disabled`
---
### `gnomad://variant/{dataset}/{variantId}` <sub>resource</sub>
- Population record for one variant as `application/json`, mirroring `gnomad_get_variant`; `variantId` takes a chrom-pos-ref-alt ID or an rsID
- Typed errors: `invalid_variant_id`, `mitochondrial_unsupported`, `variant_not_found`, `ambiguous_rsid` (with `candidates`), `graphql_error`, `upstream_build_mismatch`, `upstream_unavailable`, `upstream_timeout`, `upstream_access`, and `invalid_upstream_response`, each with a recovery hint
---
### `gnomad://gene/{dataset}/{gene}/constraint` <sub>resource</sub>
- Gene loss-of-function constraint as `application/json`, mirroring `gnomad_get_gene_constraint` (same `constraint_release` per `dataset`); `gene` takes an HGNC symbol or Ensembl gene ID
- Typed errors: `gene_not_found`, `invalid_constraint_data`, `graphql_error`, `upstream_unavailable`, `upstream_timeout`, `upstream_access`, and `invalid_upstream_response`, each with a recovery hint
---
### `gnomad_variant_triage` <sub>prompt</sub>
- Arguments: `variant` required (chrom-pos-ref-alt or rsID; a malformed one is rejected); `gene` and `dataset` optional. `dataset` is one of `gnomad_r4`, `gnomad_r3`, `gnomad_r2_1`, `exac`, and the server default applies when omitted
- Emits a three-step chain as one user message: population frequency (`gnomad_get_variant`) → gene constraint (`gnomad_get_gene_constraint`) → callability check (`gnomad_get_coverage` on the exact position)
## Features
Built on [`@cyanheads/mcp-ts-core`](https://github.com/cyanheads/mcp-ts-core): stdio and Streamable HTTP transports, pluggable auth (`none` / `jwt` / `oauth`), swappable storage (`in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`), structured logging with optional OpenTelemetry tracing.
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 (`GNOMAD_MAX_CONCURRENCY`, default 2) and exponential backoff against a community-funded, rate-limited API
- In-conversation SQL analytics: `gnomad_list_gene_variants` and `gnomad_search_clinvar` stage results too large to inline on a DuckDB-backed canvas table — `gnomad_dataframe_describe` lists its columns, `gnomad_dataframe_query` runs SQL over every row
Agent-friendly output:
- Per-ancestry allele-frequency vector returned in full, never collapsed to a single global AF
- `gnomad_get_variant` returns per-item `failed[]` rows instead of failing the whole batch
- Effective `dataset` and `reference_genome` echoed on every response; null upstream fields stay null
- Every error carries a typed `reason` (e.g. `incoherent_build`, `invalid_target`, `variant_not_found`, `upstream_timeout`, `canvas_disabled`) and a recovery hint
## Getting started
### Public Hosted Instance
A public instance is available at `https://gnomad-genetics.caseyjhand.com/mcp` — no installation required. Point any MCP client at it via Streamable HTTP:
```json
{
"mcpServers": {
"gnomad-genetics-mcp-server": {
"type": "streamable-http",
"url": "https://gnomad-genetics.caseyjhand.com/mcp"
}
}
}
```
### Self-Hosted / Local
Add the following to your MCP client configuration file. gnomAD is a free, keyless API — no credentials required.
```json
{
"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):
```json
{
"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:
```json
{
"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:
```sh
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` — `@duckdb/node-api` ships as a dependency, so nothing extra to install.
### Prerequisites
- [Bun v1.4.0](https://bun.sh/) 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:**
```sh
git clone https://github.com/cyanheads/gnomad-genetics-mcp-server.git
```
2. **Navigate into the directory:**
```sh
cd gnomad-genetics-mcp-server
```
3. **Install dependencies:**
```sh
bun install
```
4. **Configure environment:**
```sh
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.
| Variable | Description | Default |
|:---------|:------------|:--------|
| `GNOMAD_API_BASE_URL` | gnomAD GraphQL endpoint. Override for a private mirror or testing. | `https://gnomad.broadinstitute.org/api` |
| `GNOMAD_DEFAULT_DATASET` | Dataset used when a tool call omits `dataset` (`gnomad_r4` / `gnomad_r3` / `gnomad_r2_1` / `exac`). | `gnomad_r4` |
| `GNOMAD_REQUEST_TIMEOUT_MS` | Per-request timeout against the GraphQL endpoint, in milliseconds. | `30000` |
| `GNOMAD_MAX_CONCURRENCY` | Cap on concurrent upstream requests — politeness against a community-funded API. | `2` |
| `GNOMAD_MAX_VARIANT_BATCH` | Maximum variant IDs accepted per `gnomad_get_variant` call. | `25` |
| `CLINVAR_BASE_URL` | NCBI E-utilities base URL for `gnomad_search_clinvar`. | `https://eutils.ncbi.nlm.nih.gov/entrez/eutils` |
| `NCBI_API_KEY` | Optional NCBI key. Raises the E-utilities rate limit from 3 to 10 req/s. | — |
| `CANVAS_PROVIDER_TYPE` | Set to `duckdb` to enable the spill/SQL path behind the list tools. When `none`, they return a capped inline preview. | `none` |
| `GNOMAD_DATAFRAME_DROP_ENABLED` | Gate for the opt-in `gnomad_dataframe_drop` tool. Off by default. | `false` |
| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http`. | `stdio` |
| `MCP_HTTP_PORT` | Port for the HTTP server. | `3010` |
| `MCP_AUTH_MODE` | Auth mode: `none`, `jwt`, or `oauth`. | `none` |
| `MCP_LOG_LEVEL` | Log level (RFC 5424). | `info` |
| `OTEL_ENABLED` | Enable [OpenTelemetry instrumentation](https://github.com/cyanheads/mcp-ts-core/tree/main/docs/telemetry). | `false` |
See [`.env.example`](./.env.example) for the full list of optional overrides.
## Running the server
### Local development
- **Build and run:**
```sh
# One-time build
bun run rebuild
# Run the built server
bun run start:stdio
# or
bun run start:http
```
- **Run checks and tests:**
```sh
bun run devcheck # Lint, format, typecheck, security
bun run test # Vitest test suite
bun run lint:mcp # Validate MCP definitions against spec
```
### Docker
```sh
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
| Directory | Purpose |
|:----------|:--------|
| `src/index.ts` | `createApp()` entry point — registers tools/resources/prompts and inits services. |
| `src/config` | Server-specific environment variable parsing and validation with Zod. |
| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`) and shared input schemas. |
| `src/mcp-server/resources` | Resource definitions (`*.resource.ts`). |
| `src/mcp-server/prompts` | Prompt definitions (`*.prompt.ts`). |
| `src/services/gnomad` | gnomAD GraphQL client, query documents, and domain types. |
| `src/services/clinvar` | NCBI E-utilities client for the optional ClinVar tool. |
| `src/services/canvas-accessor.ts` | Module-level accessor for the framework's optional DataCanvas. |
## Development guide
See [`CLAUDE.md`/`AGENTS.md`](./CLAUDE.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
## Data attribution
gnomAD data is provided by the [Genome Aggregation Database](https://gnomad.broadinstitute.org) (Broad Institute). ClinVar data is provided by [NCBI](https://www.ncbi.nlm.nih.gov/clinvar/).
## Contributing
Issues are welcome. Run checks and tests before submitting:
```sh
bun run devcheck
bun run test
```
## License
Apache-2.0 — see [LICENSE](LICENSE) for details.
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessSlow