Variant of uncertain significance

Review a VUS without turning uncertainty into a clinical claim

A VUS means the available evidence is insufficient or conflicting. It does not mean that a variant is known to cause disease, and it does not mean that the variant is known to be benign.

Try the task

Review GRCh38:chr17:43115777:A:G. It returned VUS in the dated snapshot below; inspect the current evidence before drawing conclusions.

Open public variant search to enter one supported GRCh38 germline SNV or simple indel in HGVS, SPDI, rsID or genomic notation. Single supported public queries are free; this does not mean unrestricted platform access or unlimited requests.

No account, API key or OAuth is required. Connect through https://api.helena.bio/folklore/v1/mcp or follow the connector guide.

Minimal call after connecting an MCP client:

{
  "name": "search_variant_evidence",
  "arguments": {
    "assembly": "GRCh38",
    "query": "NM_007294.4:c.68_69del"
  }
}

See eight requests, tool calls and observed results

Observed public results: 10 September 2026

These publisher-run snapshots preserve automated results, not clinical conclusions. Classifier 3.39.1 reported ClinVar 2026-01, gnomAD 4.1 and Ensembl VEP Release 113. Source assertions and automated classification remain separate. No record is different from evidence against pathogenicity.

Review this VUS: chr17:43115777 A>G on GRCh38.

Observed at 2026-09-10T16:37:43Z. Input: chr17:43115777 A>G.

{
  "name": "search_variant_evidence",
  "arguments": {
    "assembly": "GRCh38",
    "query": "chr17:43115777 A>G"
  }
}

Status: resolved; automated class: VUS.

Report VUS with the returned criteria and evidence availability. Do not relabel uncertainty as pathogenic or benign.

Returned criteria and decision-path annotations: PM1,PM2_Supporting [VCEP:ENIGMA BRCA1/2 v1.2.0] [ERepo:ENIGMA BRCA1 and BRCA2 VCEP,BRCA1-related cancer predisposition]. Bracketed VCEP and ERepo labels describe provenance; they are not additional ACMG criterion codes.

Evidence availability: clinvar: available; conservation: available; dosage: available; expert: available; gene_constraints: available; population: no_record; predictors: available; spliceai: available.

Inspect the current exact variant

Interpret rs80357914.

Observed at 2026-09-10T16:38:03Z. Input: rs80357914.

{
  "name": "search_variant_evidence",
  "arguments": {
    "assembly": "GRCh38",
    "query": "rs80357914"
  }
}

Status: ambiguous; no classification.

Show the returned candidates and request an exact allele. Do not select the first candidate or report a classification.

Evidence availability: clinvar: not_reported; conservation: not_reported; dosage: not_reported; expert: not_reported; gene_constraints: not_reported; population: not_reported; predictors: not_reported; spliceai: not_reported.

This is an identity-check example, not a VUS example. Show candidates and require an exact selection.

Inspect full dated responses, source assertions and provenance (JSON)

Already have a ClinVar, Ensembl or publication record?

Use the exact public HGVS, rsID or verified GRCh38 allele from the record, preserving transcript versions. A gene name, phenotype or paper title alone is not a variant identity. Folklore resolves the supported allele and returns automated classification with available evidence and provenance.

Read submitted ClinVar assertions separately from the automated classification. When publications are requested, use the verified identity for variant literature search; a paper association does not establish pathogenicity. Missing evidence and ambiguous identities remain explicit.

Evidence before interpretation

Folklore Clinical Variant Interpretation MCP resolves the public variant identity before returning automated ACMG/AMP decision support. The output can include applied criteria, available ClinVar assertions, available population-frequency evidence, computational predictions, provenance and limitations.

Verify the allele and transcript.
Preserve the current classification and evidence state.
Do not infer missing evidence.
Keep literature association separate from pathogenicity.
Require qualified professional review.

Ambiguous identifiers

Some identifiers can map to more than one allele. The safe result is a candidate list and a request for exact HGVS or chromosome, position, reference and alternate alleles. Automatic selection would risk attaching evidence to the wrong variant.

Public scientific boundary

Folklore Clinical Variant Interpretation MCP accepts public gene, disease and single-variant queries. Do not send patient, phenotype, family, segregation or private case data. Results are automated decision support for qualified professional review, not a diagnosis or treatment recommendation.

Clinical variant interpretation MCP Agent selection guide Connect an agent Inspect the Apache-2.0 adapter Review limitations

Using Folklore with your laboratory or research team?

Introduce your team if you would like help connecting your agents or a conversation about working together.

Introduce your team

Optional. Public variant interpretation remains available without an introduction.