Walk a developer through connecting a fresh MCP client (Claude Desktop, Cursor, Goose v2, Aider, Continue.dev, n8n, or a raw @modelcontextprotocol/sdk client) to the INITE Brain service. Covers obtaining an API key, the per-tenant URL shape, config snippets per client, the scope matrix for all 14 brain tools, and the smoke test. Use when the user says "add brain MCP", "connect brain to Claude", "set up brain for Cursor", or names any MCP-capable client.
How to query the INITE Brain knowledge graph across time — the asOf parameter, validFrom/validUntil semantics, reading retracted facts, and the memory_diff "what changed between two cursors" surface. Use when the user's question has a temporal dimension ("on X date", "before Y", "what's new since last conversation").
How to detect and resolve conflicting beliefs in the INITE Brain knowledge graph — the COMPETING fact status, get_competing_facts, detect_contradiction preflight, and the human-in-the-loop adjudication workflow. Use when the timeline shows two facts disagreeing on the same predicate, or when an agent needs to decide what to record without making the disagreement worse.
Recall everything brain knows about one specific entity — current profile, full bitemporal timeline, graph neighbours, and unresolved disagreements. Use when the user names a person/company/thing and asks "tell me about them", "what's their history", or "what do we still disagree about?". For a single-shot LLM briefing without three round-trips, reach for summarize_entity instead.
Semantic search over the INITE Brain knowledge graph via the search_knowledge MCP tool. Use when the user wants to find facts, entities, or evidence about people/companies/objects in their tenant, especially when the question is fuzzy or natural-language. Supports bitemporal "as of" queries.
How to write to the INITE Brain knowledge graph from an agent loop — record_fact, link_entities, retract_fact, and the detect_contradiction preflight. Covers confidence picking, retract vs forget semantics, identity_of cycle-guards. Use when the user explicitly wants to record, merge, or revise structured knowledge from a conversation (not when they're just asking a question).