Natural-language retrieval over Little Big Brain. Use query for one phrasing, queries for reciprocal-rank fusion across phrasings, and follow_paths: true when you want bounded graph paths from text-resolved seed entities. When you can judge returned results, call lbb_commit mode=search_feedback with good=3, partial=1, bad=0 so Little Big Brain can build customer-specific qrels for embedding training.

Name the relation between two entities from the admissible published vocabulary. Types may be omitted and resolved from entity names.

Ground terms to the graph's published vocabulary. complete autocompletes a prefix, resolve snaps free text to real vocabulary, and audit reports graph groundability.

Read graph context and exact graph facts. Actions: guide, ontology, ontology_conformance, schema, ontology_search, metadata, entity, state, history, transitions, why, traverse. schema reads active ontology/SHACL bundle metadata without running validation. ontology_conformance serves the durable report referenced by the pinned published root. entity returns one node's metadata, scalar attributes, bounded edge neighborhood, history, and observations. Use traverse for bounded path expansion or lbb_query for precise SPARQL edge selection.

Analytical and expert reads. Modes: structured (SPARQL-subset JSON body), sparql (SPARQL text), analyze. Relations are https://littlebigbrain.com/r/NAME and types https://littlebigbrain.com/class/NAME (both lowercased); entities are content-addressed, so anchor a named one by its rdfs:label rather than building its IRI. Structured and text queries pin one published watermark for the request.

Read model-training inputs or compare retrieval configurations over one pinned published snapshot. shadow_eval takes the API ShadowEvalRequest body; dataset actions return bounded training examples at an optional signal split.

Write graph facts, retract them, or label search results. mode=facts writes triplets/embeddings/properties; mode=retract removes a wrongly-added fact (by edge or by entity) without a full reset; mode=search_feedback labels query/result relevance after lbb_search (Feedback grades: 3=ideal/good, 1=partial, 0=bad; include query, search_id when available, target, rank, score). Explicit idempotency_key wins; when omitted, MCP derives a stable content hash so content-identical retries dedupe. Facts mode defaults edge_idempotency to append; pass skip_unchanged for re-runnable backfills.

Mutate stored graph configuration. Actions: define_ontology, evolve_ontology, and publish_schema. Schema publication atomically activates metadata and enqueues durable conformance; it never validates the whole graph in the request.

Branch lifecycle. Actions: create (fork a new branch off from_branch — the tool's branch argument names the NEW branch) and merge (validate-then-merge: replay from_branch's post-fork commits onto the scoped target branch — its fork parent — as ONE commit with event ids preserved; SHACL-validates the would-be merged state first and refuses with the report on violations; a fact superseded on the target after the fork wins over the branch's version, reported as a supersedure_race conflict; delete_source consumes the merged branch).

Remember a conversation: store the turns verbatim as an EPISODE evidence entity, then anchor + gate the supplied facts on an observe branch (LLM extraction cannot poison the main graph). Facts with both endpoints already in the graph are anchored; unanchored facts need confidence >= 0.8 to mint new entities, else they come back needs_review. auto_merge merges the branch onto the scoped branch when SHACL validation is clean (the validate-then-merge). Server flag-gated (--enable-observe). This build takes caller-extracted facts (each with a structured triplet); bare statements come back needs_review.