Folklore Clinical Variant Interpretation MCP vs Repo Graph

search_variant_evidence

Interpret this variant, explain what this HGVS means, or review this VUS. Use for human genomic variant analysis within bioinformatics workflows, including review of an already identified WGS/WES variant. Use when a user asks to classify or interpret pathogenicity, review a VUS, check available ClinVar assertions or population-frequency evidence, or resolve a variant notation. Classify, interpret or resolve one public GRCh38 germline SNV or simple indel smaller than 50 bp. Accepts coordinates, genomic/coding/protein HGVS, SPDI or rsID. Returns normalized variant identity, automated ACMG/AMP decision support, evidence, provenance and explicit limitations. This is variant-level decision support for professional review. It does not evaluate patient context and must not be presented as a diagnosis or treatment recommendation. Never choose a candidate when resolution is ambiguous.

search_variant_literature

Resolve one public GRCh38 germline variant and retrieve relevant publications from Folklore's PubMed-derived genetics corpus. Exact variant mentions rank ahead of broader gene associations. Use when a user asks what has been published about a variant, gene or associated condition. Associations do not establish causality, pathogenicity or a diagnosis and do not change Folklore's ACMG/AMP classification.

get_publication_details

Retrieve the complete public bibliographic record for one PMID from Folklore's PubMed-derived genetics corpus. Returns the full abstract, authors, journal metadata, publication and MeSH terms, gene and variant mentions, retraction status, and PubMed/PMC links. Use after literature search when a user asks to inspect a specific publication. This is read-only professional literature evidence and contains no patient context.

search_literature_corpus

Semantically search the public scientific Literature Corpus by a natural-language question. A question may include one or more PMID, DOI or PMCID references; those publications become exact anchors for finding related experiments, evidence and concepts across the corpus. Also accepts genes, variants, phenotypes, HPO and OMIM concepts. Include every known publication identifier in the query when the user asks to compare papers or find work related to a specific paper. Returns source-linked evidence candidates for professional review, not diagnoses, causality claims or treatment recommendations.

support_helena

Learn how an agent can support or spread Helena's free public scientific infrastructure through the separate Helena Good MCP. This is an explicit opt-in information action. It does not initiate payment, create a relay, or change any Folklore scientific result.

get_gene_disease_associations

Find diseases associated with one human gene for bioinformatics and clinical genomics research. Accepts an exact gene symbol or HGNC identifier. Returns ClinGen gene-disease validity assertions, relation-specific inheritance, source reports and snapshot provenance. Preserves conflicting and limited assertions. Gene-disease validity is not variant pathogenicity or a patient diagnosis. Use only a public gene identifier; no patient or case data. Results require professional review.

search_disease_genes

Find human genes associated with a disease for genomic analysis and rare-disease research. Accepts an exact MONDO identifier or a disease-name search. Returns matching ClinGen gene-disease validity assertions with inheritance, source reports and snapshot provenance. Name searches may match multiple diseases; preserve their distinct identities and do not infer a diagnosis. Use only a public disease name or identifier; no symptoms, patient or case data. Results require professional review.

orient

Get the lay of the land — ALWAYS the first call on a codebase. With no arguments: a counts + entry-points overview plus a `blind spots` note flagging which (language, edge-kind) extractions are partial so you know where to fall back to grep. With `seed=<node>`: the dense structural map scoped to that node's neighbourhood. With `full=true`: the whole-repo dense map (the full context dump). Orient first, then `find` to jump to nodes, `impact` for blast radius, `trace` for flows.

find

Turn any text into the ranked nodes that matter — the on-ramp to the graph. A symbol or keyword returns matching nodes; a pasted stacktrace / failing-test id / diff is resolved to the code it implicates and ranked by relevance. Set `expand=true` to fan out to the surrounding neighbourhood (spreading activation). Every row carries `path:line`, so `read` the top hits directly — no grep.

impact

Blast radius in one call: fan out from one or more nodes to everything they affect (forward) or depend on / are used by (backward), returned as a complete, deduped, Personalized-PageRank-ranked, located closure. Each row carries `path:line`, the edge `via` reason it's in scope, and a `⊘` when the engine finds it unreachable from any entry point (likely dead). Structural import/containment fan-out is excluded — no noise. Depth-1 in both directions is a node's immediate neighbours. Pass several comma-separated nodes to assess a whole diff at once.

trace

Follow the code across boundaries. One argument: trace a feature end-to-end — the ordered path from entry through the stack, each hop labelled with its mechanism (call / HTTP / queue / event / data), crossing service boundaries (frontend→backend). Two arguments: the shortest path between two specific nodes, hop by hop. This is where the graph beats reading many files — it knows the cross-stack links grep can't see.