Skip to main content
Glama

gnomad-genetics-mcp-server

gnomad-genetics-mcp-server: get variant

gnomad_get_variant
Read-onlyIdempotent

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/

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
datasetNognomAD dataset: gnomad_r4 (GRCh38, default), gnomad_r3 (GRCh38), gnomad_r2_1 (GRCh37), exac (GRCh37). Echoed in output.
variantsYes1–25 variant IDs (chrom-pos-ref-alt or rsID) to look up in one batched call.
reference_genomeNoReference build. Derived from dataset when omitted (v4/v3=GRCh38, v2.1/ExAC=GRCh37). If supplied it must match the dataset, or the call is rejected. Keep aligned with ensembl coordinates.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
foundNoVariants resolved to a population record.
failedNoPer-item failures, in input order: malformed IDs, variants absent from the dataset, or upstream errors — each with its reason and recovery hint.
noticeNoNon-fatal notice when optional ClinVar annotation was unavailable.
datasetNoEffective gnomAD dataset used for the batch.
reference_genomeNoEffective reference build used for the batch.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changed
    • changedInput schema / properties / variants / items / description
      Previous value: -"Variant ID — chrom-pos-ref-alt (1-based, e.g. 1-55051215-G-GA) or an rsID (rs11591147). Obtain a variantId from ensembl_predict_variant or a VCF. Malformed IDs are reported per-item in failed[], not rejected wholesale."New value: +"Variant ID — chrom-pos-ref-alt (1-based, e.g. 1-55051215-G-GA) on chromosome 1–22, X, or Y with an optional chr prefix, or an rsID (rs11591147). Mitochondrial IDs (M, MT, chrM) are not served. Obtain a variantId from ensembl_predict_variant or a VCF. Malformed IDs are reported per-item in failed[], not rejected wholesale."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `incoherent_build`: reference_genome was supplied but does not match the dataset. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `incoherent_build`: reference_genome was supplied but does not match the dataset. `invalid_variant_id`: A variant ID is outside the chrom-pos-ref-alt or rsID grammar; reported per item in failed[]. `variant_not_found`: A well-formed ID is absent from the requested dataset; reported per item in failed[]. `mitochondrial_unsupported`: A variant ID names the mitochondrial chromosome (M, MT, or chrM); reported per item in failed[]. `ambiguous_rsid`: An rsID maps to more than one variant in the dataset; reported per item in failed[]. `graphql_error`: gnomAD rejected the lookup for one ID with a GraphQL error; reported per item in failed[]. `upstream_build_mismatch`: gnomAD answered one ID with a variant on a different reference build; reported per item in failed[]. `upstream_unavailable`: gnomAD stayed unavailable or throttled through every retry for one ID; reported per item in failed[]. `upstream_timeout`: Every attempt to reach gnomAD for one ID timed out; reported per item in failed[]. `upstream_access`: gnomAD refused the request for one ID (access denied); reported per item in failed[]. `invalid_upstream_response`: gnomAD kept answering one ID with a response that failed validation; reported per item in failed[]. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
      -  "incoherent_build"
      -]New value: +[
      +  "incoherent_build",
      +  "invalid_variant_id",
      +  "variant_not_found",
      +  "mitochondrial_unsupported",
      +  "ambiguous_rsid",
      +  "graphql_error",
      +  "upstream_build_mismatch",
      +  "upstream_unavailable",
      +  "upstream_timeout",
      +  "upstream_access",
      +  "invalid_upstream_response"
      +]
    • changedOutput schema / properties / failed / description
      Previous value: -"Per-item failures: malformed IDs, variants absent from the dataset, or upstream errors."New value: +"Per-item failures, in input order: malformed IDs, variants absent from the dataset, or upstream errors — each with its reason and recovery hint."
    • changedOutput schema / properties / failed / items / description
      Previous value: -"One failed input ID and why it failed."New value: +"One failed input ID, why it failed, and what to do next."
    • changedOutput schema / properties / failed / items / properties / error / description
      Previous value: -"What went wrong and how to resolve it."New value: +"What went wrong for this ID."
    • addedOutput schema / properties / failed / items / properties / reason
      Added value: +{
      +  "description": "Why this ID failed — a reason declared in this tool's error contract. Branch on it rather than on the message.",
      +  "enum": [
      +    "invalid_variant_id",
      +    "variant_not_found",
      +    "mitochondrial_unsupported",
      +    "ambiguous_rsid",
      +    "graphql_error",
      +    "upstream_build_mismatch",
      +    "upstream_unavailable",
      +    "upstream_timeout",
      +    "upstream_access",
      +    "invalid_upstream_response"
      +  ],
      +  "type": "string"
      +}
    • addedOutput schema / properties / failed / items / properties / recovery
      Added value: +{
      +  "description": "The next step for this ID — the recovery hint declared for its reason.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / failed / items / required
      Previous value: -[
      -  "variant",
      -  "error"
      -]New value: +[
      +  "variant",
      +  "error",
      +  "reason",
      +  "recovery"
      +]
    • addedOutput schema / properties / found / items / properties / in_silico / items / properties / annotation
      Added value: +{
      +  "description": "Text gnomAD attaches to the score — on gnomad_r3, the SpliceAI event (e.g. acceptor_gain, no_consequence). Holds the raw text when value is null for lack of a number; null for a plain score.",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • changedOutput schema / properties / found / items / properties / in_silico / items / properties / id / description
      Previous value: -"Predictor name (e.g. revel_max, cadd, spliceai_ds_max)."New value: +"Predictor name. Ids vary by dataset — gnomad_r4: cadd, revel_max, spliceai_ds_max, pangolin_largest_ds, phylop, sift_max, polyphen_max; gnomad_r3: cadd, revel, splice_ai, primate_ai; gnomad_r2_1 and exac carry none."
    • changedOutput schema / properties / found / items / properties / in_silico / items / properties / value / description
      Previous value: -"Predictor score; null when not provided for this variant."New value: +"Predictor score; null when not provided for this variant, or when gnomAD gave text with no number (the text is then in annotation)."
    • changedOutput schema / properties / found / items / properties / in_silico / items / required
      Previous value: -[
      -  "id",
      -  "value"
      -]New value: +[
      +  "id",
      +  "value",
      +  "annotation"
      +]
  2. Changed17 schema fields changed
    • removedOutput schema / properties / found / items / properties / af / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / found / items / properties / af / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • changedOutput schema / properties / found / items / properties / clinvar / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "description": "Joined ClinVar significance from gnomAD. Null when the variant has no ClinVar entry.",
      -    "properties": {
      -      "clinical_significance": {
      -        "anyOf": [
      -          {
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "description": "ClinVar clinical significance (e.g. Pathogenic, Likely benign); null when no entry."
      -      },
      -      "clinvar_variation_id": {
      -        "anyOf": [
      -          {
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "description": "ClinVar VariationID."
      -      },
      -      "gold_stars": {
      -        "anyOf": [
      -          {
      -            "type": "number"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "description": "ClinVar 0–4 star review rating."
      -      },
      -      "review_status": {
      -        "anyOf": [
      -          {
      -            "type": "string"
      -          },
      -          {
      -            "type": "null"
      -          }
      -        ],
      -        "description": "ClinVar review status text."
      -      }
      -    },
      -    "required": [
      -      "clinical_significance",
      -      "review_status",
      -      "gold_stars",
      -      "clinvar_variation_id"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "description": "Joined ClinVar significance from gnomAD. Null when the variant has no ClinVar entry.",
      +    "properties": {
      +      "clinical_significance": {
      +        "description": "ClinVar clinical significance (e.g. Pathogenic, Likely benign); null when no entry.",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "clinvar_variation_id": {
      +        "description": "ClinVar VariationID.",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      },
      +      "gold_stars": {
      +        "description": "ClinVar 0–4 star review rating.",
      +        "type": [
      +          "number",
      +          "null"
      +        ]
      +      },
      +      "review_status": {
      +        "description": "ClinVar review status text.",
      +        "type": [
      +          "string",
      +          "null"
      +        ]
      +      }
      +    },
      +    "required": [
      +      "clinical_significance",
      +      "review_status",
      +      "gold_stars",
      +      "clinvar_variation_id"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / properties / found / items / properties / consequence / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / found / items / properties / consequence / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / found / items / properties / gene_symbol / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / found / items / properties / gene_symbol / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / found / items / properties / hemizygote_count / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / found / items / properties / hemizygote_count / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / found / items / properties / in_silico / items / properties / value / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / found / items / properties / in_silico / items / properties / value / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / found / items / properties / populations / items / properties / af / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / found / items / properties / populations / items / properties / af / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / found / items / properties / populations / items / properties / hemizygote_count / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / found / items / properties / populations / items / properties / hemizygote_count / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / found / items / properties / transcript_id / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / found / items / properties / transcript_id / type
      Added value: +[
      +  "string",
      +  "null"
      +]
  3. Changed4 schema fields changed
    • addedOutput schema / properties / failed / items / properties / candidates
      Added value: +{
      +  "description": "Concrete variant IDs to retry when an rsID is ambiguous.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / found / items / properties / clinvar_unavailable
      Added value: +{
      +  "description": "True when the optional ClinVar resolver failed; false when no entry exists.",
      +  "type": "boolean"
      +}
    • changedOutput schema / properties / found / items / required
      Previous value: -[
      -  "variant_id",
      -  "rsids",
      -  "reference_genome",
      -  "dataset",
      -  "ac",
      -  "an",
      -  "af",
      -  "homozygote_count",
      -  "hemizygote_count",
      -  "populations",
      -  "source",
      -  "flags",
      -  "consequence",
      -  "transcript_id",
      -  "gene_symbol",
      -  "in_silico",
      -  "clinvar"
      -]New value: +[
      +  "variant_id",
      +  "rsids",
      +  "reference_genome",
      +  "dataset",
      +  "ac",
      +  "an",
      +  "af",
      +  "homozygote_count",
      +  "hemizygote_count",
      +  "populations",
      +  "source",
      +  "flags",
      +  "consequence",
      +  "transcript_id",
      +  "gene_symbol",
      +  "in_silico",
      +  "clinvar",
      +  "clinvar_unavailable"
      +]
    • addedOutput schema / properties / notice
      Added value: +{
      +  "description": "Non-fatal notice when optional ClinVar annotation was unavailable.",
      +  "type": "string"
      +}
  4. First observed

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnly, idempotent, openWorld), and the description adds genuinely useful behavioral detail beyond them: batch cap of 25 with per-item partial success where malformed/absent IDs land in failed[] with a reason and recovery hint rather than failing the batch, empty-result semantics, the fixed dataset options with defaults, and the derived reference build. It even states that mitochondrial IDs are not served.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the return payload, then the batching/failure semantics, then the data source. The long enumeration of returned fields is dense but informative; nearly every sentence earns its place, though the field list could be tightened slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't explain return values, and it covers everything else an agent needs: batch limits, partial-failure handling, empty-result interpretation, dataset/reference-build coupling, and the coverage cross-check. Nothing material is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents variants, dataset, and reference_genome with their enums and defaults. The description restates the batch size and ID formats but adds no syntax or format detail beyond the schema, so the baseline 3 is appropriate when the schema carries the parameter burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Fetch) and resource (full gnomAD population record for one or more variants) and enumerates the payload: allele counts/frequency per ancestry group, homozygote/hemizygote counts, quality flags, transcript consequence, in-silico scores, ClinVar significance. It also frames the scope ('the how common, is it benign answer in one call') and names the complementary sibling gnomad_get_coverage, so an agent can place it among the other gnomad_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete usage context: batching up to 25 IDs in one call, per-item partial success, and the key interpretive rule that an empty found[] means the variant is not in the chosen dataset — with the explicit instruction to pair with gnomad_get_coverage before concluding true absence. It names an alternative with its selecting condition, but does not explicitly exclude sibling tools like gnomad_search_clinvar for clinical-only lookups.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.