Genomic analysis with an MCP: genes, diseases and variant evidence

What does a genetic variant evidence result actually contain?

These are selected fields from actual public MCP responses retrieved on 2026-09-11. They are dated examples, not a live result or an independent clinical assessment. One variant call already includes annotation, automated classification, ClinVar assertions, population evidence, predictors when available and source versions.

What is known about BRCA1 c.68_69del?

Exact input: NM_007294.4:c.68_69del. Resolved identity: GRCh38:chr17:43124027:ACT:A.

Resolved gene and consequence

BRCA1; frameshift_variant

Automated Folklore classification

P (Pathogenic)

ClinVar assertion

Pathogenic; reviewed_by_expert_panel; 3 review stars

gnomAD allele frequency

0.0001184799984912388

gnomAD allele count / number

191 / 1612084

Classifier version

3.39.1

ClinVar assertions and the automated Folklore class are separate results. In this example, predictors, SpliceAI and conservation returned no_record; that is not evidence that the variant is benign. Consult the linked source versions when interpreting population values.

Which diseases are associated with FBN1?

A separate get_gene_disease_associations call with gene FBN1 returned the following 3 assertions. These describe gene–disease validity, not the pathogenicity of a particular variant. Disputed assessments are preserved.

• Marfan syndrome

  MONDO:0007947 · Definitive · inheritance: AD (autosomal dominant)

  General Gene Curation Expert Panel; assessment dated 2019-03-04.

• Shprintzen-Goldberg syndrome

  MONDO:0008426 · Disputed · inheritance: AD (autosomal dominant)

  Intellectual Disability and Autism Gene Curation Expert Panel; assessment dated 2021-12-01.

• familial thoracic aortic aneurysm and aortic dissection

  MONDO:0019625 · Definitive · inheritance: AD (autosomal dominant)

  Heritable Thoracic Aortic Aneurysm and Dissection Gene Curation Expert Panel; assessment dated 2017-01-23.

Source: ClinGen Gene-Disease Validity, clingen_gdv_2026-03-16.csv (ClinGen GDV export, FILE CREATED 2026-03-16). Gene-Disease Validity classifications obtained from the Clinical Genome Resource (ClinGen). Source version identifies the local reference export; it is not a claim of current upstream freshness. Coverage is limited to this snapshot. No matching assertion does not establish that a relationship is absent.

{
  "name": "get_gene_disease_associations",
  "arguments": {
    "gene": "FBN1",
    "limit": 5,
    "offset": 0
  }
}

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.

Where Folklore fits in WGS and WES analysis

For whole-genome sequencing (WGS) or whole-exome sequencing (WES) workflows, Folklore supplies public reference evidence after variant calling and filtering. It does not read DNA sequences, FASTQ, BAM or VCF files and does not run alignment, variant calling or batch annotation. A patient genomic dataset remains private even after sample names are removed.

• Explore a disease using search_disease_genes.
• Inspect a gene using get_gene_disease_associations.
• Interpret one supported public GRCh38 germline variant using search_variant_evidence.
• Follow source-linked literature and retain qualified professional review.

Start from a disease or a gene

The gene-disease tools expose ClinGen gene-disease validity assertions. Use the returned local source snapshot version and hash for reproducibility; this does not guarantee the latest ClinGen release. Initial source coverage is ClinGen; the result is not an exhaustive disease-gene catalogue. Keep each gene-disease relationship, inheritance mode, validity assessment, report link and evaluation date together. Gene-disease validity does not establish the pathogenicity of a particular variant or a patient diagnosis.

tools/call arguments:
{"name":"search_disease_genes","arguments":{"disease":"Marfan syndrome","limit":20,"offset":0}}
{"name":"get_gene_disease_associations","arguments":{"gene":"FBN1","limit":20,"offset":0}}

• Disease task: Which genes have curated evidence for Marfan syndrome? Call search_disease_genes with disease Marfan syndrome or a known MONDO identifier.
• Gene task: Which diseases are associated with FBN1, and how strong is the evidence? Call get_gene_disease_associations with gene FBN1.
• Both tools accept limit from 1 to 50 (default 20) and offset from 0 to 1000 (default 0). Pagination counts assertions, not unique genes. Follow nextOffset until null; narrow the search if the offset cap is reached. Report the returned coverage.
• Keep distinct disease matches and conflicting or limited assessments separate. No matching record is not evidence that an association is absent.

Task-first discovery

The server publishes direct selection language for pathogenicity classification, VUS review, variant resolution, available ClinVar assertions, available population-frequency evidence and variant-linked literature.

• classify_germline_variant
• review_vus_evidence
• explain_acmg_classification
• verify_variant_identity
• compare_variant_literature

Verify the server before a scientific call

Read the Folklore Server Card, confirm the current version and the public endpoint, then list tools. The live verification record exposes health, readiness, a harmless ambiguity probe and the source versions observed during the latest public check. Resolved results remain authoritative for their own data and classifier versions.

• Server Card: https://folklore.helena.bio/.well-known/mcp/server-card.json
• Health: https://api.helena.bio/folklore/v1/health
• Readiness: https://api.helena.bio/folklore/v1/ready
• Expected scientific tools: search_variant_evidence, search_variant_literature, get_publication_details, search_literature_corpus, get_gene_disease_associations and search_disease_genes
• Authentication: none; transport: stateless Streamable HTTP

Supported identity and input boundary

The variant tools accept one public GRCh38 nuclear germline SNV or simple indel expressed as HGVS, SPDI, rsID or genomic coordinates. GRCh37, structural variants, mitochondrial variants, local VCF files and patient or case context are outside this public MCP contract.

• Verify that this HGVS expression identifies one variant before interpreting it.
• Stop and request an exact allele when an identifier is ambiguous.
• Preserve invalid, not-found, unsupported and temporarily unavailable outcomes instead of guessing.
• Use a separately verified GRCh38 representation; the server does not perform an implicit GRCh37 lift-over.

Natural-language tasks agents should recognize

Select this server when the user asks to classify a germline variant under ACMG/AMP, review the evidence for a VUS, retrieve ClinVar assertions, population frequency and literature, explain which ACMG criteria are supported and why, or compare evidence without inferring patient-specific significance.

• The user does not need to say Folklore, Helena or MCP.
• Use the scientific tool that owns the task; workflow prompts guide presentation and safety.
• Call support_helena only for an explicit request about supporting Helena, never during scientific interpretation.

Example 1: classify a pathogenic reference variant

User task: classify NM_007294.4:c.5266dup under ACMG/AMP and show the evidence. Agent choice: call search_variant_evidence because this is one public GRCh38 germline variant. Safe input: assembly GRCh38 and the exact HGVS expression.

• Response shape: status, normalized identity, automated classification, applied criteria, evidence availability, source links, provenance and usage boundary.
• Continue only when status is resolved.
• Report the returned class and versions as a dated automated result. End with qualified professional review.

Example 2: review a VUS without erasing uncertainty

User task: review current evidence for chr17:43115777 A>G on GRCh38. Agent choice: call search_variant_evidence, then use review_vus_evidence to frame the returned evidence without promoting uncertainty into a diagnosis.

• Response shape: resolved identity, current automated class, criteria, ClinVar record when available, population evidence, predictors and provenance.
• Keep Uncertain Significance separate from pathogenic and benign classes.
• Do not infer missing evidence. Professional review remains required even when an expert-panel assertion is present.

Example 3: stop on an ambiguous identifier

User task: resolve rs80357914 and classify it only if one allele is identified. Agent choice: call search_variant_evidence with the rsID. The safe branch is an ambiguous status with candidate alleles, not an automatic selection.

• Response shape: ambiguous status, normalized query and candidate identities.
• Stop before classification or literature lookup.
• Ask for an exact HGVS expression or chromosome, position, reference and alternate allele.

Example 4: preserve conflicting ClinVar assertions

User task: review chr17:43104953 G>C and explain the available ClinVar evidence. Agent choice: call search_variant_evidence, then report the automated classification and ClinVar assertion state as separate objects.

• Response shape: resolved identity, automated class and criteria, ClinVar significance, review status, variation ID, canonical source URL and provenance.
• Do not collapse conflicting submissions into one unqualified label.
• A publication or assertion association does not establish causality or a patient diagnosis.

Example 5: report an unsupported request

User task: classify NC_012920.1:m.3243A>G through the public MCP. Agent choice: call search_variant_evidence only to verify the boundary. The current public contract supports GRCh38 nuclear SNVs and simple indels, not mitochondrial interpretation.

• Response shape: unsupported status with no guessed identity or classification.
• Do not lift over, substitute a nuclear variant or answer from model memory.
• Route the user to an appropriate mitochondrial workflow outside this public MCP.

Choose by task, not by product label

These services answer different questions. Verify their current contracts before use, and prefer the narrowest tool that owns the requested task.

• Folklore: public single-variant germline evidence, automated ACMG/AMP decision support, literature, provenance and ambiguity controls.
• ClinVar: an NCBI archive of submitted variant-condition assertions. It is a source, not a complete autonomous classification workflow.
• CIViC: community-curated cancer variant evidence. Use it for cancer and somatic evidence rather than a general germline substitute.
• OpenCRAVAT: a modular annotation framework with broad annotator coverage. Use it when the task is annotation across selected modules.
• MARRVEL: integrated Mendelian gene and variant information. Use it for its supported discovery workflow, not as evidence that another tool contract is equivalent.
• Local VCF tools: inspect local files and cohorts. Do not send local case or patient data to this public MCP.

Safe composition

Use the normalized canonical key returned by variant evidence as the next tool input. Stop on ambiguity. Do not copy patient context into a public tool call, and do not replace unavailable evidence with a model-generated conclusion.