MCP server

INITE Brain Official

io.github.inite-ai/inite-brain-service

Checked 26 Oct 2026, 08:29 UTC · Not tested (older connection type)

Long-term memory for AI agents: a bitemporal knowledge graph with cited answers.

Website Source

At a glance

Type

MCP server

Publisher

inite.ai (verified by the MCP Registry)

Status

Not checked

Tools

30

Last checked

26 Oct 2026, 08:29 UTC

Tools

• about_brain ~67 tokens
  What this server is and what it can do, before you connect. Reads nothing and stores nothing.
• detect_contradiction ~518 tokens
  Dry-run preflight against fn::resolve_fact. Answers "if I were to record this fact right now, what would the resolver decide?" without writing to the database. wouldOutcome ∈ {INSERTED, SUPERSEDED, COMPETING, REJECTED}; reasoning explains which rule fired (semantics class, score gap vs margin, cosin
• find_entity_communities ~133 tokens
  Returns the topic communities a given entity is a member of. Places an entity in its broader context — which clusters / themes it participates in — and leads from one entity to the wider neighbourhood the cluster summarises.
• find_related_entities ~215 tokens
  Get entities connected to the given one via the knowledge graph.
• get_competing_facts ~358 tokens
  Returns facts in COMPETING status — those the conflict resolver couldn't auto-supersede because two same-predicate bitemporal facts overlap in valid-time and are too cosine-close within margin. Grouped by (entityId, predicate); 2-fact groups are pairs the resolver left for adjudication, 3+-fact grou
• get_entity_profile ~232 tokens
  Full profile of one entity: canonical name, type, externalRefs (cross-vertical ids), and active facts. externalRefs point back to the originating vertical, where fresh state can be rehydrated via @inite/api-kit.
• get_entity_timeline ~182 tokens
  Chronological audit of all facts brain has learned about this entity, including retracted ones. Useful for "what did we know when" investigations.
• get_fact ~245 tokens
  Read a single fact as stored — predicate (aspect), object (statement), confidence, validity window, source attribution (vertical / recorder / conversationId), and lifecycle state. Retracted facts still resolve (retracted: true) — "why did I stop remembering this" is part of the trust story; only vis
• get_fact_provenance ~245 tokens
  Return the grounding provenance behind one fact: the verbatim conversation turns it was derived from (episodes, chronological, with char-span quotes when the deriver stamped them). When the server runs with the recursive-closure flag the response additionally carries derivedFacts + closure (the tran
• get_source_reputation ~241 tokens
  Return everything brain knows ABOUT a source (not its facts): the operator-declared identity (type, authLevel — authority in conflict resolution), the learned per-domain agreement rates (domain = predicate; null domain = the global blended rate; rates need >=8 samples before the resolver trusts them
• graph_retrieve ~357 tokens
  Resolves the named entities by canonical name, walks their 1-hop neighbourhood over knowledge_edge, and returns facts across seeds ∪ neighbours, optionally filtered by predicate hints. Works from entities named up front and returns what the graph holds around them ("who runs engineering at Acme" — t
• how_to_connect ~98 tokens
  The two ways to authenticate, and what each is for. Reads nothing and stores nothing.
• link_entities ~417 tokens
  Insert an edge between two entities. `kind` is the edge type — `identity_of` merges the `from` entity into `to` (cross-vertical identity reconciliation), other typed edges (`paid_for`, `mentioned_in`, `worked_with`, …) are surfaced in related-entity reads and contribute to PPR / SubgraphRAG context.
• list_communities ~102 tokens
  Paginated listing of topic communities, largest first. Each row carries a label, a rolled-up summary, and the member count. Gives the knowledge map at a glance.
• list_procedures ~110 tokens
  Paginated listing of procedural memory for admin/review UIs. Sorted by priority ASC, createdAt DESC. Set includeRetired=true to see soft-deleted rows.
• match_procedure ~235 tokens
  Cosine-matches procedural memory (curated 'how to' patterns the operator recorded) against a free-text context query. Returns top-K procedures sorted by similarity DESC then priority ASC. Surfaces the behaviour rules that apply to a context — e.g. "user asks about pricing" → "mention they're on plat
• memory_diff ~426 tokens
  Returns everything brain learned, unlearned, or replaced between two ISO 8601 cursors [from, to). createdFacts = new active facts; retractedFacts = facts marked retracted in-window with no successor; changedFacts = facts that were superseded by another (carries before+after); newEntities = entities
• recall_decisions ~171 tokens
  Find recorded design decisions / rationale / invariants / gotchas by NL topic ("why do we resolve facts through one gateway?"), across ALL code anchors — a semantic search over code-memory, rather than one known anchor. Returns matches with their code anchor + kind, ranked by relevance.
• record_decision ~415 tokens
  Capture the non-derivable engineering "why" about a code location: a design decision, its rationale, an invariant that must hold, or a gotcha. Anchored to a SCIP-style symbol or file path (NOT line numbers — survives edits). Stored as a bitemporal typed fact: re-recording a `decided` / `invariant` f
• record_fact ~617 tokens
  Insert a fact about an entity. Triggers brain conflict resolution (INSERTED / SUPERSEDED / COMPETING / REJECTED). Most facts come from event ingestion; this records one directly.
• record_procedure ~284 tokens
  Record a 'how to' pattern that is surfaced when a similar context appears later. trigger = the context phrase the rule should match against (e.g. "user asks about pricing"); action = the behaviour to apply (e.g. "mention they're on platinum tier; they get 20% off"). priority orders ties when multipl
• retire_procedure ~137 tokens
  Mark a procedural memory row as retired (sets retiredAt). A retired procedure is no longer matched or listed by default. For a rule that no longer applies — distinct from a hard delete because the row stays for audit.
• retract_fact ~218 tokens
  Mark a fact as no longer believed. Cascades to facts derived from this one. Does not delete; the row remains for audit.
• search_communities ~250 tokens
  Cosine-matches the query against topic-community summaries — the coarse retrieval scope. A community is a cluster of related entities (label propagation over the entity graph) with one rolled-up summary. Suited to broad questions ("what do we know about X domain"): it returns an overview of a domain
• search_knowledge ~347 tokens
  Semantic search over the company knowledge graph. Returns entities with their top facts and external references back to the originating verticals. Apply asOf for historical "what was true on X" queries (valid time: a fact brain learned after X still shows). Embedding model on this tenant: set per wo
• search_multi_hop ~553 tokens
  Planner-LLM decomposes the query into ≤ maxHops anchored sub-queries; later hops are anchored to the running entity set so the engine never spends compute on candidates already disqualified. Built for questions that combine evidence across turns / sessions, or that require reasoning over multiple en
• summarize_entity ~477 tokens
  Returns a short one-line briefing about the entity — name, type, the most-confident active facts, external refs — suitable for dropping into an LLM context window. Caches in-process (per companyId / entityId / asOf / styleHint) so a hot entity touched across many turns doesn't reload the profile. st
• synthesize ~408 tokens
  Runs hybrid search then feeds the retrieved facts to a generator LLM that produces a citation-bearing answer (each claim ends with [factId]); a verifier LLM then judges whether every claim is supported. Three guardrail modes: strict (default) returns null on partial / unsupported / verifier outage (
• why ~265 tokens
  Return the design decisions, rationale, invariants and gotchas recorded against a code anchor — the non-derivable engineering "why" a parser cannot recover from source. The anchor is a SCIP-style symbol string ("pkg/namespace/symbol") or a file path ("repo/path/file.ts"). Pass asOf to recall what wa
• workspace_status ~236 tokens
  The tenant this credential writes to (companyId, its display name, whether it is a personal workspace), what is already in its memory (entities, active facts, facts recorded in the last 7 days), how many Domain Packs are installed, for a user-bound connection who the user is in this memory (`user.na

Browse

• GitHub tools
• GitHub and code hosting
• Databases
• Memory for agents
• Searching your documents (RAG)

Related MCP servers

• INITE
  INITE itself: services and prices, free call slots, booking a call, writing to the team. No token.
• Aidelly
  Agent-operated social media for agencies — www.aidelly.ai. Post, approve, analyze on 11 networks.
• CortexPlus
  Personal memory layer: files, notes, messages, tasks and email, semantically indexed.
• Bordet AI
  Ask a room of Claude, GPT and Gemini from your AI tool, search its memory and log decisions.
• Palim
  Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.
• Onehaus Haus
  OneHaus household tools: tasks, calendar, contacts, pets, vehicles, documents and more.
• AiAkiv Memory
  Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.
• Humaux Memory
  Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.inite-ai/inite-brain-service.svg)](https://aptlynx.net/servers/io.github.inite-ai/inite-brain-service)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents