@littlebigbrain/mcp

lbb_inspect

Read-only

Inspect exact graph facts, ontology, schema, entity metadata, history, and publication status to understand knowledge graph state.

Instructions

Read graph context and exact graph facts. Actions: guide, graphs, publication, ontology, ontology_conformance, schema, ontology_search, metadata, entity, state, history, transitions, why. graphs works before bootstrap; publication reports whether writes are queryable. ontology and schema return complete entries with page_size, section and cursor; follow next until absent. schema reads active native ontology/SHACL metadata without running validation. Query asserted RDF/OWL axioms separately with lbb_query. ontology_conformance serves the durable report referenced by the pinned published root. entity returns one node's metadata, scalar attributes, bounded Base-backed edge neighborhood, history, and observations. Use lbb_query with SPARQL property paths for precise path selection.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No
`as_of`	No	Valid-time snapshot pin (RFC3339): reproduce the node as of this instant.
`graph`	No	Graph to target; defaults to the connection's graph
`query`	No	Ontology concept, term, or relation to search
`top_k`	No
`action`	Yes	Selects the variant (one of: guide, ontology, ontology_conformance, schema, graphs, publication, ontology_search, metadata, entity, state, history, why, transitions).
`branch`	No	Branch to target; defaults to the connection's branch
`cursor`	No	Opaque lbb_inspect continuation. Repeat action and pass the returned next arguments; rejects changed metadata.
`detail`	No	Response detail level. Defaults to compact.
`section`	No	Optional top-level array to inspect, e.g. entity_type_defs, relation_defs, property_defs, classes, or relations. Omit to page through all sections.
`relation`	No
`entity_id`	No	Entity id (hex); alternative to entity_type+name
`page_size`	No	Maximum complete metadata entries per page; defaults to 50. Nested fields are never truncated; an oversized single entry returns serialized_json fragments to concatenate and parse.
`entity_type`	No
`source_name`	No
`source_type`	No
`target_name`	No
`target_type`	No
`as_of_commit_seq`	No	Snapshot pin: reproduce the node (state, edges, history) as of this commit_seq.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.5.1Sep 19, 2026

changedInput schema / properties / action / description

Previous value: -"Selects the variant (one of: guide, ontology, ontology_conformance, schema, ontology_search, metadata, entity, state, history, why, transitions)."New value: +"Selects the variant (one of: guide, ontology, ontology_conformance, schema, graphs, publication, ontology_search, metadata, entity, state, history, why, transitions)."

changedInput schema / properties / action / enum

Previous value: -[
-  "guide",
-  "ontology",
-  "ontology_conformance",
-  "schema",
-  "ontology_search",
-  "metadata",
-  "entity",
-  "state",
-  "history",
-  "why",
-  "transitions"
-]New value: +[
+  "guide",
+  "ontology",
+  "ontology_conformance",
+  "schema",
+  "graphs",
+  "publication",
+  "ontology_search",
+  "metadata",
+  "entity",
+  "state",
+  "history",
+  "why",
+  "transitions"
+]

addedInput schema / properties / cursor

Added value: +{
+  "description": "Opaque lbb_inspect continuation. Repeat action and pass the returned next arguments; rejects changed metadata.",
+  "type": "string"
+}

addedInput schema / properties / page_size

Added value: +{
+  "description": "Maximum complete metadata entries per page; defaults to 50. Nested fields are never truncated; an oversized single entry returns serialized_json fragments to concatenate and parse.",
+  "maximum": 500,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / section

Added value: +{
+  "description": "Optional top-level array to inspect, e.g. entity_type_defs, relation_defs, property_defs, classes, or relations. Omit to page through all sections.",
+  "type": "string"
+}

Changed5 schema fields changedv0.4.2Aug 28, 2026

changedInput schema / properties / action / description

Previous value: -"Selects the variant (one of: guide, ontology, ontology_conformance, schema, ontology_search, metadata, entity, state, history, why, traverse, transitions)."New value: +"Selects the variant (one of: guide, ontology, ontology_conformance, schema, ontology_search, metadata, entity, state, history, why, transitions)."

changedInput schema / properties / action / enum

Previous value: -[
-  "guide",
-  "ontology",
-  "ontology_conformance",
-  "schema",
-  "ontology_search",
-  "metadata",
-  "entity",
-  "state",
-  "history",
-  "why",
-  "traverse",
-  "transitions"
-]New value: +[
+  "guide",
+  "ontology",
+  "ontology_conformance",
+  "schema",
+  "ontology_search",
+  "metadata",
+  "entity",
+  "state",
+  "history",
+  "why",
+  "transitions"
+]

removedInput schema / properties / direction

Removed value: -{
-  "enum": [
-    "out",
-    "in",
-    "both"
-  ],
-  "type": "string"
-}

removedInput schema / properties / max_hops

Removed value: -{
-  "exclusiveMinimum": 0,
-  "maximum": 6,
-  "type": "integer"
-}

removedInput schema / properties / relations

Removed value: -{
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

Changed12 schema fields changedv0.2.7Jul 30, 2026

changedInput schema / properties / action / description

Previous value: -"Selects the variant (one of: guide, ontology, ontology_conformance, schema, schema_audit, rules, schema_preview, ontology_search, metadata, entity, edges, state, history, why, traverse, transitions)."New value: +"Selects the variant (one of: guide, ontology, ontology_conformance, schema, ontology_search, metadata, entity, state, history, why, traverse, transitions)."

changedInput schema / properties / action / enum

Previous value: -[
-  "guide",
-  "ontology",
-  "ontology_conformance",
-  "schema",
-  "schema_audit",
-  "rules",
-  "schema_preview",
-  "ontology_search",
-  "metadata",
-  "entity",
-  "edges",
-  "state",
-  "history",
-  "why",
-  "traverse",
-  "transitions"
-]New value: +[
+  "guide",
+  "ontology",
+  "ontology_conformance",
+  "schema",
+  "ontology_search",
+  "metadata",
+  "entity",
+  "state",
+  "history",
+  "why",
+  "traverse",
+  "transitions"
+]

removedInput schema / properties / base_ontology_version

Removed value: -{
-  "minimum": 0,
-  "type": "integer"
-}

removedInput schema / properties / base_shapes_version

Removed value: -{
-  "minimum": 0,
-  "type": "integer"
-}

removedInput schema / properties / cursor

Removed value: -{
-  "description": "Opaque cursor from the previous page's `next_cursor`. The response is the unified list envelope { object:'list', data, has_more, next_cursor, total_count }; page a high-degree node (entity detail hard-caps its edge sample) by feeding next_cursor back here until has_more is false. Each row carries valid_time for a per-edge timeline.",
-  "type": "string"
-}

removedInput schema / properties / desired_mode

Removed value: -{
-  "enum": [
-    "warn",
-    "reject"
-  ],
-  "type": "string"
-}

removedInput schema / properties / direction / description

Removed value: -"Edges out of / into / touching the entity (default both)."

removedInput schema / properties / offset

Removed value: -{
-  "description": "Legacy alias for `cursor` (still accepted); prefer paging with `cursor`.",
-  "minimum": 0,
-  "type": "integer"
-}

removedInput schema / properties / ontology

Removed value: -{
-  "additionalProperties": false,
-  "properties": {
-    "format": {
-      "enum": [
-        "auto",
-        "turtle",
-        "json_ld",
-        "rdf_xml",
-        "csv",
-        "tsv",
-        "lbb_json",
-        "spec"
-      ],
-      "type": "string"
-    },
-    "source": {
-      "description": "Ontology source text",
-      "type": "string"
-    }
-  },
-  "required": [
-    "source"
-  ],
-  "type": "object"
-}

removedInput schema / properties / relation / description
```
Removed value: -"Filter to a single relation name."
```

removedInput schema / properties / row_limit

Removed value: -{
-  "description": "Max edges returned this page (server caps at 1000; default 150).",
-  "exclusiveMinimum": 0,
-  "type": "integer"
-}

removedInput schema / properties / shapes

Removed value: -{
-  "additionalProperties": false,
-  "properties": {
-    "format": {
-      "enum": [
-        "auto",
-        "turtle",
-        "n_triples",
-        "n_quads",
-        "trig"
-      ],
-      "type": "string"
-    },
-    "source": {
-      "description": "SHACL/RDF shape source text",
-      "type": "string"
-    }
-  },
-  "required": [
-    "source"
-  ],
-  "type": "object"
-}

First observedv0.2.1Jul 11, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint=true already covering the read-only profile, the description productively adds behavior: pagination mechanics ('follow next until absent'), queryability reporting, and 'schema reads active native ontology/SHACL metadata without running validation'. It also describes entity's bounded edge neighborhood. It stops short of outlining error cases or exact response shapes, but is not contradicted by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

At roughly 130 words, the description is dense but front-loads purpose, then gives action-specific behavior in compact clauses. Each sentence adds either routing, pagination, or variant semantics; the action enumeration is a necessary structural element rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 19-parameter, 13-action tool with no output schema, the description covers the major variants, pagination, and the key sibling alternative. However, several actions (guide, state, history, transitions, why, metadata) are only named and not described, and some parameter interactions are left implicit, so it is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 58%, so the schema still carries much of the parameter burden. The description adds semantics for action, page_size, section, and cursor, but leaves several parameters (name, relation, entity_type, source_name, target_name, etc.) with no explanation beyond the schema, some of which have no schema description either.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Read graph context and exact graph facts', a specific verb + resource, then enumerates the 13 action variants. It distinguishes itself from lbb_query by directing asserted RDF/OWL axiom queries to that sibling, though it does not explicitly differentiate against lbb_rdf, so it falls just short of full clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides actionable routing signals: 'Query asserted RDF/OWL axioms separately with lbb_query', 'Use lbb_query with SPARQL property paths for precise path selection', and lifecycle context such as 'graphs works before bootstrap' and 'publication reports whether writes are queryable'. It does not give exclusions for other siblings like lbb_rdf or lbb_models, so usage guidance is clear but incomplete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

lbb_inspect

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools