INITE Brain
Long-term memory for AI agents: a bitemporal knowledge graph with cited answers
Reviews
No review yet. Used INITE Brain? Be the first to help others choose.What it does
INITE Brain is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.
No capability identified yet from its description.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 8h ago (live check)Hosted endpoints
https://brain.inite.ai/mcpstreamable-httphttps://brain.inite.ai/mcp/{companyId}streamable-http
In Claude Code: claude mcp add --transport http inite-brain https://brain.inite.ai/mcp
The endpoint contains a placeholder to replace with your own value (see the publisher's docs).
Required: Authorization (get it from the publisher)
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"inite-brain": {
"url": "https://brain.inite.ai/mcp"
}
}
}Live check
Electra Index connected to the hosted endpoint 8h agoONLINE INITE Brain answered an MCP connection on 17 Nov 2026 and introduced itself as inite-brain-service 2.11.0 (MCP protocol 2025-06-18).
32 tools offered to AI assistants
about_brain· What this server is and what it can do, before you connect, and whether the server's own models (embeddings, chat) are currently available. Reads nothing and stores nothing.how_to_connect· The two ways to authenticate, and what each is for. Reads nothing and stores nothing.search_knowledge· Semantic search over the company knowledge graph: the facts the query is about, the links between their entities and what was left out. Apply asOf for historical "what was true on X" queries. Embedding model on this tenant: set per workspacsearch_multi_hop· Planner-LLM decomposes the query into ≤ maxHops anchored sub-queries; later hops are anchored to the running entity set. Built for questions that combine evidence across turns / sessions, or that require reasoning over multiple entities ("tgraph_retrieve· 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 thesynthesize· 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 (defaulmemory_diff· 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 supersedeget_entity_profile· One entity: canonical name, type and what brain holds about it now; detail "full" adds externalRefs, the ids of its records in the originating vertical.get_entity_timeline· Chronological audit of all facts brain has learned about this entity, including retracted ones. Useful for "what did we know when" investigations.summarize_entity· 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 entget_competing_facts· 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 groupdetect_contradiction· 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 w
Show 20 more
get_fact· 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 Iget_fact_provenance· 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 refind_related_entities· Get entities connected to the given one via the knowledge graph.match_procedure· 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 contextlist_procedures· Paginated listing of procedural memory for admin/review UIs. Sorted by priority ASC, createdAt DESC. Set includeRetired=true to see soft-deleted rows.search_communities· 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 dolist_communities· 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.find_entity_communities· 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.why· 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 arecall_decisions· 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 withget_source_reputation· 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 blendedworkspace_status· 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 usrecord_fact· Records one fact about an entity directly; the memory settles it against the facts it holds (INSERTED / SUPERSEDED / COMPETING). Most facts arrive through ingestion.link_entities· 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 relatretract_fact· Mark a fact as no longer believed. Cascades to facts derived from this one. Does not delete; the row remains for audit.record_procedure· 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 platinumretire_procedure· 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.record_decision· 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 bittake_memory_work· Returns the next batch of work the memory left for a connected model, in this order: predicate_semantics (new attributes: one value at a time or several), media_reading (images to read: their text verbatim and what they show; the images folsubmit_memory_work· Stores a model's JSON reply to a batch of memory work, with its work token. The server applies it with its own code: extraction replies are grounded against the text it handed out, resolved and committed; attribute classifications update th
What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method
Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Version | 2.11.0 | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Hosted endpoint | https://brain.inite.ai/mcp, https://brain.inite.ai/mcp/{companyId} | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Local install (package) | no | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Remote access (hosted) | yes | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Website | https://brain.inite.ai | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Repository | https://github.com/inite-ai/inite-brain-service | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 1d ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 1d ago |
Change history
- VERSION14 Nov 20262.10.0 → 2.11.0
- VERSION14 Nov 20262.9.0 → 2.10.0
- VERSION13 Nov 20262.8.1 → 2.9.0
- VERSION13 Nov 20262.8.0 → 2.8.1
- VERSION13 Nov 20262.7.0 → 2.8.0
- VERSION03 Nov 20262.6.0 → 2.7.0
- VERSION29 Oct 20262.5.1 → 2.6.0
- VERSION27 Oct 20262.5.0 → 2.5.1
- VERSION27 Oct 20262.4.0 → 2.5.0
- VERSION16 Oct 20262.3.0 → 2.4.0
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is INITE Brain still online?
Free alerts · no account▲ 0Do you run INITE Brain? Know when it stops answering
For publishers · optionalIts hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.
Monitoring never changes a score or a rank.
Questions about INITE Brain
How do I connect INITE Brain?
Use the hosted endpoint https://brain.inite.ai/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
Does INITE Brain need an API key or token?
Yes. The registry entry lists a required value: Authorization. Get it from the publisher.
What tools does INITE Brain offer?
When Electra Index connected on 17 Nov 2026, it listed 32 tools: about_brain, how_to_connect, search_knowledge, search_multi_hop, graph_retrieve, synthesize, memory_diff, get_entity_profile and more. The full list is in "Live check" above.
Is INITE Brain online?
Yes. Its hosted endpoint answered an MCP connection from Electra Index 8h ago.