INITE Brain is answering right now. Last checked 6 min ago. It exposes 30 tools. Last commit 8 Nov 2026.
Long-term memory for AI agents: a bitemporal knowledge graph with cited answers.
Uptime history
91 days of history · worst day 53%
91 days agonow
100.0%
Uptime 24h
184 of 184 checks
30
Tools
read from the server
647 ms
Response time
average over 24h
43
Stars
last commit 8 Nov 2026
What changed 16
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 3 November 2026. No other catalogue keeps this.
3 Nov
12 tools changed the parameters they ask for
get_entity_profile, get_entity_timeline, get_fact and 9 more
3 Nov
4 tool descriptions were rewritten
get_entity_profile, record_fact, search_knowledge and 1 more
What the code does
We read the source, 17 h ago · tools taken from the live server · rules 995398eba69f
Capabilities
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
Runs an external command
brain-landing/app/sitemap.ts:13, plugins/inite-brain/hooks/brain-hook.mjs:282
const iso = execSync(`git log -1 --format=%cI -- "${relPath}"`, {
Builds a file path from a variable
brain-landing/lib/blog.ts:50, brain-landing/lib/docs.ts:16
return path.join(BLOG_DIR, lang)
Executes code built at runtime
src/admin/admin-packs.controller.ts:132
async eval(
Asks for container control access
monitoring/docker-compose.yml:86
- /var/run/docker.sock:/var/run/docker.sock:ro
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
run in your terminal
claude mcp add inite-brain-service --transport http 'https://brain.inite.ai/mcp/{companyId}'Settings → Connectors → Add custom connector, then paste this address
https://brain.inite.ai/mcp/{companyId}~/.codex/config.toml
[mcp_servers.inite-brain-service]
url = "https://brain.inite.ai/mcp/{companyId}".cursor/mcp.json
{
"mcpServers": {
"inite-brain-service": {
"url": "https://brain.inite.ai/mcp/{companyId}"
}
}
}.vscode/mcp.json
{
"servers": {
"inite-brain-service": {
"type": "http",
"url": "https://brain.inite.ai/mcp/{companyId}"
}
}
}This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.
Available tools 30
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
entity
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.
get_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.
record
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 bitemporal typed fact: re-recording a `decided` / `invariant` for the same anchor SUPERSEDES the prior one (decision evolution over time), while `because` / `gotcha` accumulate. Attach commit / location for provenance.
record_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.
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 platinum tier; they get 20% off"). priority orders ties when multiple procedures match the same context (lower is higher priority; default 100). decayHalfLifeDays is a forward hook for v0.2 relevance decay; v1 ignores it at read time.
communities
list_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.
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 do we know about X domain"): it returns an overview of a domain rather than individual facts. Communities are (re)built off-hours by the dreams loop; an empty result means clustering has not run or the graph is too sparse.
fact
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 I stop remembering this" is part of the trust story; only visibility fences turn into not-found. groundingStatus (grounded | ungrounded) appears on facts stamped by the claim-grounding plane (EVIDENCE_GROUNDING_STAMP); legacy rows carry no key. Same shape as GET /v1/facts/:id. Takes a factId as returned by searches and writes and returns the full trust record behind it.
get_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 response additionally carries derivedFacts + closure (the transitive derivedFrom support graph); a plain deployment returns episodes only — the response is a passthrough of GET /v1/facts/:id/provenance, no field filtering. Traversal depth is a server-side policy (flag + caps), not a caller knob. Lets a surprising fact be audited before it is trusted or retracted.
about
about_brain
What this server is and what it can do, before you connect. Reads nothing and stores nothing.
competing
get_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 groups are pairs the resolver left for adjudication, 3+-fact groups are multi-way disagreements escalated for human review. Answers "is this entity already conflicted on this predicate?" and can drive an in-product reviewer queue. asOf filters to disagreements that were live at that moment.
detect
detect_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 which rule fired (semantics class, score gap vs margin, cosine threshold, etc); opposingFacts lists the same-predicate priors the resolver would have weighed against. Useful where the cost of a contested write is high (e.g. agent loops that pay an ingest credit). Fidelity: this preflight uses the SEED source-trust table and authority 0 — the live resolver scores opponents with the learned domain-scoped rates (migration 0045) and declared source authority (migration 0046), so predictions can differ for sources with conflict history or a registered authLevel.
graph
graph_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 the graph holds around them ("who runs engineering at Acme" — the answer lives on a neighbour, not on Acme itself). Seeds score 1.0, neighbours 0.7; soft-fails to an empty result.
how
how_to_connect
The two ways to authenticate, and what each is for. Reads nothing and stores nothing.
knowledge
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 workspace.
link
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 related-entity reads and contribute to PPR / SubgraphRAG context. Most edges come from event ingestion; this inserts one directly. identity_of rejects a request that names the same end twice and any merge that would close a cycle; declaring an identity that already holds answers `alreadyIdentical: true` with no edge, so a replay is safe.
match
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 context — e.g. "user asks about pricing" → "mention they're on platinum tier; they get 20% off". Procedural memory is the third tier alongside facts (semantic) and episodes (timeline).
memory
memory_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 superseded by another (carries before+after); newEntities = entities created in-window; forgottenEntities = GDPR-erased tombstones; lapsedExpectations = temporary states (ill, away) whose expected end passed in-window with nothing confirming or ending them — worth asking about. Driving use case: "what changed since the last conversation?" Scope with entityIds and/or predicates to narrow the diff to a feature surface. Window is half-open; consecutive diffs over adjacent windows never double-count.
multi
search_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 ("tenants who complained in April AND upgraded after"). Set synthesize=true to get a grounded answer with citations alongside the per-hop trace. Returns the hops, the answer when asked, and the evidence as focus lines. Embedding model on this tenant: set per workspace.
procedures
list_procedures
Paginated listing of procedural memory for admin/review UIs. Sorted by priority ASC, createdAt DESC. Set includeRetired=true to see soft-deleted rows.
recall
recall_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 with their code anchor + kind, ranked by relevance.
related
find_related_entities
Get entities connected to the given one via the knowledge graph.
retire
retire_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.
retract
retract_fact
Mark a fact as no longer believed. Cascades to facts derived from this one. Does not delete; the row remains for audit.
source
get_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 blended rate; rates need >=8 samples before the resolver trusts them over the neutral 0.5), and the reputation-over-time history. sourceKey is `vertical:recorder` (recorder falls back to `_`) — the same key facts carry in trustSnapshot.sourceKey. Shows how much weight a fact whose trustSnapshot looks surprising deserves.
summarize
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 entity touched across many turns doesn't reload the profile. styleHint='neutral' | 'sales' | 'support' are template-rendered (no LLM call). styleHint='client_llm' opts into MCP SAMPLING: brain asks the connected client (Claude Desktop / agent runtime) to write the one-liner with its own model — zero brain-side OpenAI cost, perfect for self-hosters who don't want brain holding an LLM key. Falls back to neutral template + sampledBy='local_template' when the client doesn't advertise sampling capability. A briefing in place of the full profile, timeline and competing facts.
synthesize
synthesize
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 (fail-closed); lenient returns the answer alongside the verifier verdict; off skips the verifier. Returns a direct natural-language answer rather than raw search results. Embedding model on this tenant: set per workspace.
why
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 a file path ("repo/path/file.ts"). Pass asOf to recall what was known at a past instant (bitemporal). Returns found:0 with empty memory when nothing is recorded.
workspace
workspace_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 user-bound connection who the user is in this memory (`user.name` — the name the memory has learned from them, null until it has), and `nextSteps` — the setup actions that would actually change something, derived from that state rather than a stored checklist (including asking the user how to address them, once, and recording it). Answers "which workspace am I writing to?" and explains why memory answers may look emptier than expected.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://brain.inite.ai/mcp/{companyId} | streamable-http | sign-in | 664 ms | 7 min ago |
| https://brain.inite.ai/mcp | streamable-http | answering | 699 ms | 6 min ago |
Alternatives to INITE Brain
same job, measured the same wayAgently Brain
by agently
Company brain for AI agents — temporal knowledge graph search, exploration, and durable memory.
Semurg agent memory
by semurg
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Memory
by humaux
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
AiAkiv Memory
by aiakiv
Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.
Zekra
by fadymondy
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
Memharness
by las7
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
Mnemograph
by tm42
Event-sourced knowledge graph memory for AI coding agents with semantic search
Total Agent Memory
by vbcherepanov
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
INITE Brain — questions
Answers built from our own checks of this server.
What can INITE Brain do?
It exposes 30 tools, read directly from the server on our last check. Among them: about_brain, detect_contradiction, find_entity_communities, find_related_entities, get_competing_facts, get_entity_profile and 24 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
What is INITE Brain mostly used for?
Its tools cluster around entity, record and fact. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is INITE Brain working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 184 of 184 checks got a reply (100.0%), average response time 647 ms. The bar chart above shows every period we have measured.
How do I connect INITE Brain?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to INITE Brain?
No API key is involved. INITE Brain answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is INITE Brain?
It answers our handshake in 647 ms on average, which is faster than 15% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is INITE Brain open source?
The code is open source: it is published under the AGPL-3.0 licence, written in TypeScript, 43 stars on GitHub and 14 open issues. The licence covers the code in the repository, not the hosted service at brain.inite.ai, which runs on its operator's own terms.