# io.github.cyanheads/gnomad-genetics-mcp-server

> Ancestry allele frequencies, LoF constraint, variant lists, and coverage from gnomAD, with ClinVar.

- name: io.github.cyanheads/gnomad-genetics-mcp-server
- version: 0.4.1
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 81/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fgnomad-genetics-mcp-server
- tools: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fgnomad-genetics-mcp-server/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "gnomad-genetics-mcp-server": {
      "type": "http",
      "url": "https://gnomad-genetics.caseyjhand.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% +updated-6d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 81/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 2 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 7 of 7 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: gnomad_get_gene_constraint (destructiveHint); gnomad_search_clinvar (destructiveHint); gnomad_get_variant (destructiveHint); …
- pass `tools.token_cost`: about 4,083 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 11 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know @cyanheads/gnomad-genetics-mcp-server@0.4.1, @cyanheads/gnomad-genetics-mcp-server@0.4.1

- tools: 7, about 4,083 tokens to load them all
- tool set hash: 581a6a2c938c35a40f59c5b0c833758f
- tools last changed: 2026-10-14T19:26:02.062Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.cyanheads/gnomad-genetics-mcp-server.svg)](https://protogrid.dev/servers/io.github.cyanheads/gnomad-genetics-mcp-server)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-14 `gnomad_get_coverage` changed (description, outputSchema)
  - before: Fetch gnomAD sequencing-coverage summary across a gene, transcript, or region — mean and median read depth, plus the mean fraction of samples covered at each depth threshold (1× through 100×), separated by exome and genome track. Use this to disambiguate a true absent variant from an uncallable position: a variant missing from a well-covered region is informative, while one missing from a poorly-covered region is not. Supply exactly one of gene, transcript_id, or region. The optional coverage_source narrows to one track; by default both available tracks are returned. Echoes the effective dataset and build. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
  - after: Fetch gnomAD sequencing-coverage summary across a gene, transcript, or region — mean and median read depth, plus the mean fraction of samples covered at each depth threshold (1× through 100×), separated by exome and genome track. gnomAD reports coverage in buckets: 1 bp for a region spanning under 850 bp, wider for larger targets (bucket_size), and a gene or transcript is summarized over its exons ±75 bp, not its introns. Use this to disambiguate a true absent variant from an uncallable position: a variant missing from a well-covered region is informative, while one missing from a poorly-covered region is not. Supply exactly one of gene, transcript_id, or region. The optional coverage_source narrows to one track; by default both available tracks are returned. Echoes the effective dataset and build. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
- 2026-10-14 `gnomad_get_variant` changed (outputSchema)
- 2026-09-30 `gnomad_dataframe_query` changed (description, inputSchema, outputSchema)
  - before: Run a read-only SQL SELECT against a canvas table staged by gnomad_list_gene_variants (table gene_variants) or gnomad_search_clinvar (table clinvar_variants). Use the canvas_id and table_name those tools returned to rank by allele frequency, group by consequence class, count loss-of-function variants, or filter the full set the inline preview only sampled. SELECT statements only — writes, DDL, and file/HTTP table functions are rejected by the canvas gate. Call gnomad_dataframe_describe first to discover staged table and column names.
  - after: Run a read-only SQL SELECT against a canvas table staged by gnomad_list_gene_variants (table gene_variants) or gnomad_search_clinvar (table clinvar_variants) and return one page of the result. Use the canvas_id and table_name those tools returned to rank by allele frequency, group by consequence class, count loss-of-function variants, or filter the full set the inline preview only sampled. A page holds up to limit rows (default 100, max 500) and ends early once its rows reach 10,000 characters of JSON; continue from next_offset until it is null. Each page re-runs the SQL, so stable paging needs an ORDER BY over a unique key (such as variant_id) and an unchanged table. Paging reaches the server row cap: above it total is null and later rows are reachable only by filtering or aggregating in SQL. SELECT statements only — writes, DDL, and file/HTTP table functions are rejected by the canvas gate. Call gnomad_dataframe_describe first to discover staged table and column names.
- 2026-09-30 `gnomad_search_clinvar` changed (outputSchema)
- 2026-09-30 `gnomad_get_coverage` changed (inputSchema, outputSchema)
- 2026-09-30 `gnomad_list_gene_variants` changed (inputSchema, outputSchema)
- 2026-09-30 `gnomad_get_gene_constraint` changed (description, outputSchema)
  - before: Fetch gnomAD loss-of-function constraint for a gene — pLI (probability of LoF intolerance; >0.9 intolerant), LOEUF (oe_lof_upper, the headline metric; <0.6 intolerant in v4, <0.35 in v2) plus its lower bound, observed/expected ratios for LoF, missense, and synonymous variation, and the three Z-scores. This is 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). Many genes have null constraint (sparse upstream) — null fields are reported as such, never fabricated. v4 constraint is flagged beta by the gnomAD team; constraint_flags surfaces any caveats. Echoes the effective dataset and reference build. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
  - after: Fetch gnomAD loss-of-function constraint for a gene — pLI (probability of LoF intolerance; >0.9 intolerant), LOEUF (oe_lof_upper, the headline metric) plus its lower bound, observed/expected ratios for LoF, missense, and synonymous variation, and the three Z-scores. This is 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). constraint_release names the release the metrics come from: gnomAD v4.1.2 for gnomad_r4 and gnomad_r3 (gnomAD publishes no v3 constraint), gnomAD v2.1.1 for gnomad_r2_1, and ExAC r0.3 for exac. gnomAD recommends LOEUF < 0.45 to call a gene LoF-intolerant on v4.1.2 and LOEUF < 0.35 on v2.1.1. ExAC r0.3 publishes only pLI, the Z-scores, and observed/expected counts, so on exac the ratios and LOEUF are null, constraint_flags is empty, and pLI is the intolerance measure. Many genes have null constraint (sparse upstream) — null fields are reported as such, never fabricated. Echoes the effective dataset and reference build. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
- 2026-09-30 `gnomad_get_variant` changed (description, inputSchema, outputSchema)
  - before: Fetch the full gnomAD population record for one or more variants — allele count/number/frequency overall and broken down per genetic-ancestry group, homozygote and hemizygote counts, quality flags, transcript consequence, in-silico predictor scores, and joined ClinVar clinical significance. The "how common, is it benign" answer in one call. Accepts a batch of up to 25 IDs (chrom-pos-ref-alt or rsID) with per-item partial success: a malformed or absent ID lands in failed[] without failing the others. 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. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
  - after: Fetch the full gnomAD population record for one or more variants — allele count/number/frequency overall and broken down per genetic-ancestry group, homozygote and hemizygote counts, quality flags, transcript consequence, in-silico predictor scores, and joined ClinVar clinical significance. The "how common, is it benign" answer in one call. Accepts a batch of up to 25 IDs (chrom-pos-ref-alt or rsID) with per-item partial success: a malformed or absent ID lands in failed[] — with its reason and a recovery hint — without failing the others. 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. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
- 2026-09-24 `gnomad_search_clinvar` changed (description, inputSchema, outputSchema)
  - before: Search ClinVar (NCBI E-utilities) for a gene and return its classified variants — clinical significance, review status with a 0–4 star rating, associated conditions, molecular consequences, and submission counts — turning the variant-level significance gnomAD joins into a gene-panel curation view. Optionally filter by clinical_significance (e.g. pathogenic) and a minimum star rating. The full set is staged on a DataCanvas table named clinvar_variants with an inline preview; query it with gnomad_dataframe_query to rank or count across the complete set. Keyless, but honors NCBI_API_KEY for a higher rate limit. When the canvas is disabled the tool returns a capped inline preview with spilled=false. Credit: ClinVar, NCBI.
  - after: Search ClinVar (NCBI E-utilities) for a gene and return its classified variants — clinical significance, review status with a 0–4 star rating, associated conditions, molecular consequences, submission counts, and gnomAD-compatible identifiers (canonical SPDI, rsIDs, GRCh38 variant ID for gnomad_get_variant) — turning the variant-level significance gnomAD joins into a gene-panel curation view. Optionally filter by clinical_significance (e.g. pathogenic) and a minimum star rating. Each call returns one window of up to 500 ClinVar records: total_found is the ClinVar candidate count for the search terms, taken before the significance and star filters narrow each window, and next_offset continues through the rest via offset. A window too large to inline is staged on a DataCanvas table named clinvar_variants, returned as canvas_id and table_name beside an inline preview — call gnomad_dataframe_describe for its columns, then gnomad_dataframe_query to rank or count across the window. A window that fits inline stages no table unless canvas_id is supplied. Keyless, but honors NCBI_API_KEY for a higher rate limit. When the canvas is disabled the tool returns a capped inline preview. Credit: ClinVar, NCBI.
- 2026-09-24 `gnomad_get_coverage` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fgnomad-genetics-mcp-server/changes

## Dependencies

- npm @cyanheads/gnomad-genetics-mcp-server@0.4.1: unknown
- npm @cyanheads/gnomad-genetics-mcp-server@0.4.1: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://gnomad-genetics.caseyjhand.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- npm @cyanheads/gnomad-genetics-mcp-server@0.4.1
- npm @cyanheads/gnomad-genetics-mcp-server@0.4.1

## Tools (7)

- `gnomad_dataframe_describe`: List the tables staged on a canvas and their columns (name and type) so you can write correct SQL for gnomad_dataframe_query. Use the canvas_id returned by gnomad_list_gene_variants or gnomad_search_clinvar. Returns one entry per table with its row count and column schema.
- `gnomad_dataframe_query`: Run a read-only SQL SELECT against a canvas table staged by gnomad_list_gene_variants (table gene_variants) or gnomad_search_clinvar (table clinvar_variants) and return one page of the result. Use the canvas_id and table_name those tools returned to rank by allele frequency, group by consequence class, count loss-of-function variants, or filter the full set the inline preview only sampled. A page holds up to limit rows (default 100, max 500) and ends early once its rows reach 10,000 characters of JSON; continue from next_offset until it is null. Each page re-runs the SQL, so stable paging needs an ORDER BY over a unique key (such as variant_id) and an unchanged table. Paging reaches the server row cap: above it total is null and later rows are reachable only by filtering or aggregating in SQL. SELECT statements only — writes, DDL, and file/HTTP table functions are rejected by the canvas gate. Call gnomad_dataframe_describe first to discover staged table and column names.
- `gnomad_get_coverage`: Fetch gnomAD sequencing-coverage summary across a gene, transcript, or region — mean and median read depth, plus the mean fraction of samples covered at each depth threshold (1× through 100×), separated by exome and genome track. gnomAD reports coverage in buckets: 1 bp for a region spanning under 850 bp, wider for larger targets (bucket_size), and a gene or transcript is summarized over its exons ±75 bp, not its introns. Use this to disambiguate a true absent variant from an uncallable position: a variant missing from a well-covered region is informative, while one missing from a poorly-covered region is not. Supply exactly one of gene, transcript_id, or region. The optional coverage_source narrows to one track; by default both available tracks are returned. Echoes the effective dataset and build.
Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
- `gnomad_get_gene_constraint`: Fetch gnomAD loss-of-function constraint for a gene — pLI (probability of LoF intolerance; >0.9 intolerant), LOEUF (oe_lof_upper, the headline metric) plus its lower bound, observed/expected ratios for LoF, missense, and synonymous variation, and the three Z-scores. This is 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). constraint_release names the release the metrics come from: gnomAD v4.1.2 for gnomad_r4 and gnomad_r3 (gnomAD publishes no v3 constraint), gnomAD v2.1.1 for gnomad_r2_1, and ExAC r0.3 for exac. gnomAD recommends LOEUF < 0.45 to call a gene LoF-intolerant on v4.1.2 and LOEUF < 0.35 on v2.1.1. ExAC r0.3 publishes only pLI, the Z-scores, and observed/expected counts, so on exac the ratios and LOEUF are null, constraint_flags is empty, and pLI is the intolerance measure. Many genes have null constraint (sparse upstream) — null fields are reported as such, never fabricated. Echoes the effective dataset and reference build.
Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
- `gnomad_get_variant`: Fetch the full gnomAD population record for one or more variants — allele count/number/frequency overall and broken down per genetic-ancestry group, homozygote and hemizygote counts, quality flags, transcript consequence, in-silico predictor scores, and joined ClinVar clinical significance. The "how common, is it benign" answer in one call. Accepts a batch of up to 25 IDs (chrom-pos-ref-alt or rsID) with per-item partial success: a malformed or absent ID lands in failed[] — with its reason and a recovery hint — without failing the others. 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.
Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
- `gnomad_list_gene_variants`: List every gnomAD variant in a gene, transcript, or region with allele frequencies and predicted consequences, optionally filtered to one consequence class (lof, missense, synonymous, other) and/or a maximum allele frequency. A result too large to inline is staged on a DataCanvas table named gene_variants, returned as canvas_id and table_name beside an inline preview — call gnomad_dataframe_describe for its columns, then gnomad_dataframe_query to rank by AF, count by consequence, or group across every row rather than the preview. A result that fits inline stages no table unless canvas_id is supplied. When the canvas is disabled (CANVAS_PROVIDER_TYPE != duckdb) the tool returns a capped inline preview and the SQL path is unavailable. Supply exactly one of gene, transcript_id, or region. Echoes the effective dataset and build.
Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/
- `gnomad_search_clinvar`: Search ClinVar (NCBI E-utilities) for a gene and return its classified variants — clinical significance, review status with a 0–4 star rating, associated conditions, molecular consequences, submission counts, and gnomAD-compatible identifiers (canonical SPDI, rsIDs, GRCh38 variant ID for gnomad_get_variant) — turning the variant-level significance gnomAD joins into a gene-panel curation view. Optionally filter by clinical_significance (e.g. pathogenic) and a minimum star rating. Each call returns one window of up to 500 ClinVar records: total_found is the ClinVar candidate count for the search terms, taken before the significance and star filters narrow each window, and next_offset continues through the rest via offset. A window too large to inline is staged on a DataCanvas table named clinvar_variants, returned as canvas_id and table_name beside an inline preview — call gnomad_dataframe_describe for its columns, then gnomad_dataframe_query to rank or count across the window. A window that fits inline stages no table unless canvas_id is supplied. Keyless, but honors NCBI_API_KEY for a higher rate limit. When the canvas is disabled the tool returns a capped inline preview. Credit: ClinVar, NCBI.