Repo Graph vs Folklore Clinical Variant Interpretation MCP

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.

read

Return the source code for one or more nodes, sliced from their files by the graph's line spans. Use after `find`/`impact` to read the exact code without grepping — comma-separate several node names to read the whole ranked set in a single call. Each node is a code block headed by its qname and `path:start-end`, plus a `context:` footer with structural facts the source alone doesn't show: HTTP method, cross-stack callers, covering tests, and intent/decision/constraint cells when present.

refresh

(Re)build the structural graph with tree-sitter AST parsing across 20 languages, running the cross-stack resolvers (HTTP, gRPC, GraphQL, WebSocket, queues, events, CLI). Incremental by default — only changed files re-parse — so it's cheap to call after edits; set `full=true` to force a clean reparse. Accepts a local path or a git URL (cloned on demand). Call after a major refactor; routine edits are picked up automatically by the file watcher.

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.