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

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.

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 25, capped at 3,000) and ends before a row that would take its row JSON past 4,000,000 characters; 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. BIGINT values, such as the staged ac and an counts and COUNT(*), arrive as JSON strings to keep their precision; CAST(col AS INTEGER) returns a number. 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.

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. gnomAD publishes no coverage for subsets, so a subset dataset reads its parent release (gnomad_r4_non_ukb reads gnomad_r4) over all the parent’s samples: coverage_dataset names the release read, and a notice says so. Echoes the effective dataset and build. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/

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 and gnomAD’s LOEUF percentile, observed/expected ratios for LoF, missense, and synonymous variation with 90% intervals for missense and synonymous, 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, gnomad_r3, and their subsets (gnomAD publishes no v3 constraint), gnomAD v2.1.1 for gnomad_r2_1 and its subsets, and ExAC r0.3 for exac. gnomAD publishes no subset constraint, so a subset dataset reads its parent release’s table and echoes the subset as dataset. gnomAD recommends LOEUF < 0.45 to call a gene LoF-intolerant on v4.1.2 and LOEUF < 0.35 on v2.1.1; only v4.1.2 publishes the LOEUF percentile. ExAC r0.3 publishes only pLI, the Z-scores, and observed/expected counts, so on exac the ratios, their intervals, LOEUF, and the LOEUF percentile are null, constraint_flags is empty, and pLI is the intolerance measure. A mitochondrial gene (MT-CO1, MT-TL1) has no nuclear constraint: gnomAD’s mitochondrial constraint comes back in mitochondrial_constraint instead — kind protein or rna, the same table on every dataset, exac included — and is null for every nuclear gene; the nuclear LOEUF thresholds do not apply to it. 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/

Fetch the full gnomAD population record for one or more variants — allele count/number/frequency overall and broken down per genetic-ancestry group, the filtering allele frequency (faf95) to test against a disease threshold such as ACMG/AMP BA1 or BS1, homozygote and hemizygote counts, quality flags, each callset's own counts and QC filters with a qc_status, the most severe transcript consequence with its HGVS and LOFTEE loss-of-function call (confidence, filter, flags) beside the same on the gene's MANE Select (else canonical) transcript, gnomAD's manual LoF curation verdicts, in-silico predictor scores, and joined ClinVar clinical significance. The "how common, is it benign" answer in one call. A qc_status of filtered means the variant failed gnomAD QC in every callset carrying it (gnomAD's browser hides these by default; AC0 means no high-quality carrier), so treat its counts as low-confidence rather than an observed frequency. 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. A coordinate ID carries no build: an absent one whose string also lifts over from the other build fails as variant_not_found_other_build, with the lifted IDs on the dataset's build in candidates, while a string valid on both builds can name a different variant on each, which no not-found path can see — so keep IDs on the dataset's build. variant_not_found 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/

Estimate whether two variants in the same gene sit on different haplotypes (in trans — compound heterozygous) or on the same one (in cis), from gnomAD v2.1 exome genotypes: the probability of compound heterozygosity and the genotype and haplotype counts behind it, overall and per genetic-ancestry group. For a proband with two rare heterozygous variants in a recessive gene and no parental samples. Takes exactly two GRCh37 chrom-pos-ref-alt IDs and always reads gnomad_r2_1, the only dataset gnomAD serves co-occurrence for, echoing it with GRCh37. A GRCh38 ID can name a different GRCh37 variant or none, so convert GRCh38 IDs first: gnomad_get_variant on dataset gnomad_r2_1 lists their GRCh37 IDs as candidates only when the ID fails there as variant_not_found_other_build; an ID gnomad_r2_1 finds returns a different variant. gnomAD answers only for two different coding or UTR variants of one gene, both in its exome samples with exome allele frequency of 5% or less; any other pair fails as cooccurrence_unavailable with gnomAD's reason. Each count key names variant_ids[0]'s genotype or allele first and variant_ids[1]'s second, and variant_ids can list the pair in another order than sent. The notice carries gnomAD's calibration caveat and its browser's reading of the probability. gnomAD's browser also notes when the pair is found in phase as a multi-nucleotide variant; this tool does not check for one. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/

List every gnomAD variant in a gene, transcript, or region with allele frequencies, filtering allele frequencies, zygosity counts, predicted consequences with LOFTEE's loss-of-function call, and QC status, optionally filtered to one consequence class (lof, missense, synonymous, other), a LOFTEE confidence (lof_confidence HC or LC), a maximum allele frequency, and/or a maximum filtering allele frequency (faf95_max, the value to test against a disease threshold such as ACMG/AMP BA1 or BS1). Pass annotations: true to add each row's HGVS c. and p. notation, LOFTEE filter and flags, and rsIDs. Every row carries its exome and genome QC filters and a qc_status; qc_filtered counts the matching variants that failed QC in every callset carrying them (often AC0, no high-quality carrier, at AF 0), which gnomAD's browser hides by default — read them as low-confidence, not observed variants, or pass pass_only to drop them. Each call returns one page: up to limit matching variants from offset, in gnomAD's genomic order, with total counting every match; pass next_offset as offset until it is null. gnomAD lists a target only whole, so each page re-fetches the whole target — page a large gene with filters and a large limit. At offset 0, a result too large to inline is also staged on a DataCanvas table named gene_variants holding every matching variant, returned as canvas_id and table_name — 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 one page. A result that fits inline stages no table unless canvas_id is supplied, and a page past offset 0 never stages. Supply exactly one of gene, transcript_id, or region. Echoes the resolved target, the row filters, and the effective dataset and build. Data source: gnomAD (Broad Institute) — https://gnomad.broadinstitute.org/

Search ClinVar (NCBI E-utilities) for a gene and return its classified variants — the germline clinical significance with its review status, 0–4 star rating, and conditions; any somatic oncogenicity or clinical-impact classification with its own review status and tumor types; molecular consequences, submission counts, and gnomAD-compatible identifiers (canonical SPDI, rsIDs, and a GRCh38 variant ID for gnomad_get_variant, derived from the SPDI or filled from gnomAD's own ClinVar mapping) — turning the variant-level significance gnomAD joins into a gene-panel curation view. Optionally filter by germline clinical_significance (e.g. pathogenic) and a minimum germline star rating. Each call returns one window of up to limit ClinVar records (default 10): total_found is the ClinVar count for the search terms (the match count for a mapped significance term alone, a candidate count once min_review_stars or any other term applies), 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. Credit: ClinVar, NCBI.