Skip to main content
Glama
littlebigbrains

@littlebigbrain/mcp

by littlebigbrains
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

lbb_commit

Idempotent

Write graph facts, retract wrong entries, and store search relevance labels. Use dry-run validation and idempotency keys to avoid duplicate or invalid commits.

Instructions

Write graph facts, retract them, or label ranked 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 stores query/result relevance labels (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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo
graphNoGraph to target; defaults to the connection's graph
branchNoBranch to target; defaults to the connection's branch
dry_runNoValidate a facts commit and return its structured SHACL report without writing. Only supported for mode=facts.
tripletsNo
observed_atNoBackfill timestamp (RFC3339). Records this commit AS OF that instant: stamps transaction time and defaults each triplet's valid_time.start. Replay history in order with observed_at per commit so as-of reads by date work. Omit for live writes.
retract_edgesNomode=retract: specific edges to remove, matched by (source, relation, target).
idempotency_keyNo
search_feedbackNo
edge_idempotencyNoDefaults to append in MCP. Use skip_unchanged for backfills; it skips exact current-edge duplicates and drops evidence-only repeats.
retract_entitiesNomode=retract: entities whose every current edge is removed (a current-state tombstone; the record and its history are kept for as_of reads).
entity_embeddingsNo
entity_propertiesNoTyped scalar attributes per entity. Each item is { type, name, properties }. `properties` is a flat map of field -> value, e.g. { "type": "PERSON", "name": "Ada Lovelace", "properties": { "h_index": 52, "title": "VP", "last_contact": "2026-06-26" } }. Values are coerced to each field's declared type, so a string like "2026-06-26" lands in a date_time field and "52" in an i64 field. (The verbose form [{ field, value: { i64: 52 } }] is also accepted.) Register a field first with lbb_configure evolve_ontology add_property; the commit response echoes written_properties so you can confirm what landed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.1
    • addedInput schema / properties / dry_run
      Added value: +{
+  "description": "Validate a facts commit and return its structured SHACL report without writing. Only supported for mode=facts.",
+  "type": "boolean"
+}
  2. First observedv0.2.1

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, the description discloses meaningful behavior: explicit idempotency_key wins, otherwise MCP derives a stable content hash for dedupe, facts mode defaults edge_idempotency to append, and retract removes by edge or entity while avoiding a full reset. This gives an agent a realistic model of side effects and idempotency guarantees before invoking the tool.

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

Conciseness5/5

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

The description is dense but efficient: four sentences front-load the mode taxonomy and then add idempotency/backfill behavior without fluff. This is appropriately concise for a tool with 13 parameters and three distinct operations.

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

Completeness5/5

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

For a complex multi-mode mutation tool with no output schema, the definition covers the mode contract, idempotency rules, feedback grading semantics, and backfill defaults needed to call it correctly. The schema adds detailed parameter descriptions for observed_at, edge_idempotency, retract_entities, and entity_properties, so no critical invocation detail appears missing.

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

Parameters4/5

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

With schema description coverage at 62%, the description compensates by summarizing mode-specific parameter groups and adding hard-to-infer semantics like idempotency_key behavior, edge_idempotency defaults, and the feedback grade scale. It also tells the agent which fields to include for search_feedback (query, search_id, target, rank, score). It does not re-explain every parameter, but the schema fills most of the remaining gap.

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

Purpose5/5

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

The description opens with a precise verb-plus-resource summary: 'Write graph facts, retract them, or label ranked results,' and immediately enumerates the three modes with concrete objects. It clearly identifies lbb_commit as a write/mutation tool, distinguishing it from the read-oriented siblings like lbb_query and lbb_inspect.

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?

The description gives explicit mode-selection guidance: mode=facts writes triplets/embeddings/properties, mode=retract removes wrongly-added facts without a full reset, and mode=search_feedback stores graded query/result labels. It also provides operational context such as passing skip_unchanged for re-runnable backfills. It does not name sibling tools explicitly, but the mode-level instructions make the intended usage clear.

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

Deploy Server

Other Tools