# INITE Brain (remote · brain.inite.ai)

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

- Trust score: 85/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `brain.inite.ai`: 85/100 (this document), [markdown](https://verifymcp.io/servers/inite-ai-inite-brain-service/brain.md), [page](https://verifymcp.io/servers/inite-ai-inite-brain-service/brain)
- remote · `brain.inite.ai`: 0/100, [markdown](https://verifymcp.io/servers/inite-ai-inite-brain-service/mcp-companyid.md), [page](https://verifymcp.io/servers/inite-ai-inite-brain-service/mcp-companyid)

## Channel facts

- Endpoint: `https://brain.inite.ai/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `2.7.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5018 tokens (~167/item across 30 items; 30 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 67/100
  - Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 69% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 30 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 30 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the INITE Brain MCP server?

INITE Brain is a hosted endpoint at https://brain.inite.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http inite-ai-inite-brain-service 'https://brain.inite.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "inite-ai-inite-brain-service": {
      "url": "https://brain.inite.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "inite-ai-inite-brain-service": {
      "type": "http",
      "url": "https://brain.inite.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.inite-ai-inite-brain-service]
url = "https://brain.inite.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "inite-ai-inite-brain-service": {
      "type": "remote",
      "url": "https://brain.inite.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add inite-ai-inite-brain-service --url 'https://brain.inite.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  inite-ai-inite-brain-service:
    url: "https://brain.inite.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "inite-ai-inite-brain-service": {
      "Transport": "http",
      "Url": "https://brain.inite.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add inite-ai-inite-brain-service -t streamable-http -u 'https://brain.inite.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "inite-ai-inite-brain-service": {
      "type": "http",
      "url": "https://brain.inite.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 84, 0)

- [security] Tool “get_entity_profile” rewrote its description, which is the text the model reads
- [security] Tool “record_fact” rewrote its description, which is the text the model reads
- [security] Tool “search_knowledge” rewrote its description, which is the text the model reads
- [security] Tool “search_multi_hop” rewrote its description, which is the text the model reads
- [cosmetic] “get_entity_profile” added an optional parameter “detail”
- [cosmetic] “get_entity_timeline” added an optional parameter “detail”
- [cosmetic] “get_fact” added an optional parameter “userId”
- [cosmetic] “get_fact_provenance” added an optional parameter “userId”
- [cosmetic] “graph_retrieve” added an optional parameter “userId”
- [cosmetic] “memory_diff” added an optional parameter “detail”
- [cosmetic] “recall_decisions” added an optional parameter “userId”
- [cosmetic] “search_knowledge” added an optional parameter “detail”
- [cosmetic] “search_multi_hop” added an optional parameter “detail”
- [cosmetic] “synthesize” added an optional parameter “detail”
- [cosmetic] “get_entity_profile” reworded the description of “userId”
- [cosmetic] “get_entity_timeline” reworded the description of “userId”
- [cosmetic] “memory_diff” reworded the description of “userId”
- [cosmetic] “record_fact” reworded the description of “conversationId”
- [cosmetic] “record_fact” reworded the description of “evidence”
- [cosmetic] “record_fact” reworded the description of “expectedUntil”
- [cosmetic] “record_fact” reworded the description of “userId”
- [cosmetic] “search_knowledge” reworded the description of “userId”
- [cosmetic] “summarize_entity” reworded the description of “userId”

### 2026-11-02 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (30)

### `about_brain` (~29 tokens)

About this memory server

What this server is and what it can do, before you connect. Reads nothing and stores nothing.

### `how_to_connect` (~46 tokens)

How to connect to this server

The two ways to authenticate, and what each is for. Reads nothing and stores nothing.

Input parameters:

- `client` (string): Which client you are configuring, if you want the specific instructions.

### `search_knowledge` (~226 tokens)

Search company 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.

Input parameters:

- `asOf` (string): Valid-time as-of: facts true at this ISO 8601 moment (a retraction dated before it hides the fact; a fact learned after it still shows — not a knowledge snapshot)
- `detail` (string): focus (default): only what the query is about, as facts or the source turn, whichever is shorter. compact: every fact of the matched entities, with entity ids. full: adds ids, scores, trust keys
- `limit` (integer): Max results (default 10)
- `minConfidence` (number)
- `predicates` (array): Filter to these predicates only
- `query` (string, required): Natural-language query
- `userId` (string): Whose memory: this user's personal facts beside the tenant-global ones; omit for tenant-global only

### `search_multi_hop` (~335 tokens)

Multi-hop search across the knowledge graph

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.

Input parameters:

- `asOf` (string): Valid-time as-of: facts true at this ISO 8601 moment (a retraction dated before it hides the fact; a fact learned after it still shows — not a knowledge snapshot)
- `detail` (string): answer (default): the answer and its citations, or the evidence when there is none. full: adds every hit with scores and ids
- `limit` (integer)
- `maxHops` (integer): Hard cap on planner hops (default 3, capped at 5 — beyond that latency dominates)
- `predicates` (array): Filter to these predicates only
- `query` (string, required): Natural-language query
- `synthesisGuardrails` (string): Override guardrails when synthesize=true: strict closes to null on partial; lenient returns the answer with the verifier verdict; off skips the verifier
- `synthesize` (boolean): Run the synthesizer over the final entity set and return a grounded answer with citations
- `userId` (string): Per-user memory scope: tenant-global plus this user's personal facts; omit for tenant-global only

### `graph_retrieve` (~238 tokens)

Graph-first retrieval around named entities

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.

Input parameters:

- `asOf` (string): Valid-time as-of: facts true at this ISO 8601 moment (a retraction dated before it hides the fact; a fact learned after it still shows — not a knowledge snapshot)
- `entityNames` (array, required): Canonical names of the entities to anchor on
- `predicateHints` (array): Prefer facts with these predicates (non-matching neighbour facts are dropped, seed facts kept at lower score)
- `query` (string): Free-text fallback used to resolve seeds when a name does not match exactly
- `userId` (string): Whose memory: this user's personal facts beside the tenant-global ones; omit for tenant-global only

### `synthesize` (~265 tokens)

Synthesize a grounded answer from retrieved facts

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.

Input parameters:

- `asOf` (string): Valid-time as-of: facts true at this ISO 8601 moment (not a knowledge snapshot)
- `detail` (string): answer (default): the answer and its citations, or the evidence when there is none. full: adds every hit with scores and ids
- `limit` (integer): Top-K facts fed to the generator (default 10)
- `minConfidence` (number)
- `predicates` (array)
- `query` (string, required): Natural-language question
- `synthesisGuardrails` (string): Guardrail mode (default = SYNTHESIZE_DEFAULT_GUARDRAILS env)
- `userId` (string): Per-user memory scope: tenant-global plus this user's personal facts; omit for tenant-global only

### `memory_diff` (~269 tokens)

Diff brain memory between two points in time

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.

Input parameters:

- `detail` (string): text (default): the changes per entity, one line each. full: JSON with ids
- `entityIds` (array): Scope to these entities (short or full ids)
- `from` (string, required): Inclusive lower bound (ISO 8601)
- `predicates` (array): Scope to these predicates
- `to` (string, required): Exclusive upper bound (ISO 8601)
- `userId` (string): Whose memory: this user's personal facts beside the tenant-global ones; omit for tenant-global only

### `get_entity_profile` (~152 tokens)

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.

Input parameters:

- `asOf` (string): Valid-time as-of: facts true at this ISO 8601 moment (not a knowledge snapshot)
- `detail` (string): text (default): with userId, current state as beliefs, disputes and an attribute index. compact: every current fact. full: JSON with ids
- `entityId` (string, required): Brain entity id (knowledge_entity:...) or short id
- `userId` (string): Whose memory: this user's personal facts beside the tenant-global ones; omit for tenant-global only

### `get_entity_timeline` (~127 tokens)

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.

Input parameters:

- `detail` (string): text (default): the scenes its facts came from and the state changes in each, then the rest. compact: JSON events with ids. full: adds sources
- `entityId` (string, required)
- `since` (string)
- `until` (string)
- `userId` (string): Whose memory: this user's personal facts beside the tenant-global ones; omit for tenant-global only

### `summarize_entity` (~308 tokens)

One-line briefing for an 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.

Input parameters:

- `asOf` (string): Summarize what was known at this ISO 8601 moment
- `entityId` (string, required): Brain entity id (knowledge_entity:...) or short id
- `styleHint` (string): Phrasing register — 'neutral' (default), 'sales', 'support', or 'client_llm' (delegate to client-side LLM via MCP sampling; falls back to neutral template if client doesn't support sampling)
- `userId` (string): Whose memory: this user's personal facts beside the tenant-global ones; omit for tenant-global only

### `get_competing_facts` (~223 tokens)

List competing facts for an entity

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.

Input parameters:

- `asOf` (string): Show what was competing at this ISO 8601 moment
- `entityId` (string, required): Brain entity id (knowledge_entity:...) or short id
- `predicate` (string): Filter to one predicate (e.g. "status", "address")
- `userId` (string): Per-user memory scope: preflight a user-scoped record_fact against tenant-global priors PLUS this user's personal ones. Omit for tenant-global candidates (matches record_fact's userId)

### `detect_contradiction` (~286 tokens)

Predict the conflict-resolver outcome for a candidate fact

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.

Input parameters:

- `confidence` (number)
- `entityRef` (required)
- `object` (string, required)
- `predicate` (string, required)
- `sourceVertical` (string, required): Vertical attributed as source (matches record_fact)
- `userId` (string): Per-user memory scope: preflight a user-scoped record_fact against tenant-global priors PLUS this user's personal ones. Omit for tenant-global candidates (matches record_fact's userId)
- `validFrom` (string, required)
- `validUntil` (string)

### `get_fact` (~189 tokens)

Get one fact by id

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.

Input parameters:

- `factId` (string, required): Fact id (knowledge_fact:...) or short id
- `userId` (string): Whose memory: this user's personal facts beside the tenant-global ones; omit for tenant-global only

### `get_fact_provenance` (~179 tokens)

Show why a fact is remembered (grounding 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.

Input parameters:

- `factId` (string, required): Fact id (knowledge_fact:...) or short id
- `userId` (string): Whose memory: this user's personal facts beside the tenant-global ones; omit for tenant-global only

### `find_related_entities` (~125 tokens)

Find related entities

Get entities connected to the given one via the knowledge graph.

Input parameters:

- `asOf` (string): Bitemporal edge cutoff — connections as they were believed at this ISO 8601 moment (mirrors GET /v1/entities/:id/connections?asOf=)
- `entityId` (string, required)
- `kind` (string): Edge kind filter (e.g. "paid_for", "mentioned_in")
- `userId` (string): Per-user memory scope: results include tenant-global relations plus this user's personal ones; omit for tenant-global only (fail-closed)

### `match_procedure` (~135 tokens)

Match procedural memory against a context query

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).

Input parameters:

- `limit` (integer)
- `minSimilarity` (number): Floor (default 0.4); rows below are dropped
- `query` (string, required): Natural-language context

### `list_procedures` (~60 tokens)

List recorded procedural memory entries

Paginated listing of procedural memory for admin/review UIs. Sorted by priority ASC, createdAt DESC. Set includeRetired=true to see soft-deleted rows.

Input parameters:

- `includeRetired` (boolean)
- `limit` (integer)

### `search_communities` (~141 tokens)

Search topic communities (coarse retrieval scope)

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.

Input parameters:

- `limit` (integer)
- `minSimilarity` (number): Floor (default 0.3); rows below are dropped
- `query` (string, required): Natural-language topic / domain

### `list_communities` (~51 tokens)

List topic 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.

Input parameters:

- `limit` (integer)

### `find_entity_communities` (~64 tokens)

Find the communities an entity belongs to

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.

Input parameters:

- `entityId` (string, required): knowledge_entity id

### `why` (~158 tokens)

Recall the recorded "why" behind a code symbol

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.

Input parameters:

- `asOf` (string): Bitemporal cursor — recall what was known as of this instant
- `symbol` (string, required): Code anchor — SCIP-style symbol or file path
- `userId` (string): Per-user memory scope: tenant-global decisions plus this user's own; omit for tenant-global only

### `recall_decisions` (~116 tokens)

Semantically recall code-memory across the codebase

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.

Input parameters:

- `limit` (integer)
- `query` (string, required): Natural-language topic to recall the "why" for
- `userId` (string): Per-user memory scope: tenant-global decisions plus this user's own; omit for tenant-global only

### `get_source_reputation` (~148 tokens)

Inspect the reputation of a fact source

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.

Input parameters:

- `sourceKey` (string, required): Source key, e.g. "rent:tenant_bot" or "code:_"

### `workspace_status` (~149 tokens)

What this connection is attached to, and what is left to set up

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.

### `record_fact` (~203 tokens)

Record a fact about an entity

Records one fact about an entity directly; the memory settles it against the facts it holds (INSERTED / SUPERSEDED / COMPETING). Most facts arrive through ingestion.

Input parameters:

- `confidence` (number)
- `conversationId` (string): Conversation the fact was observed in; marks it grounded
- `entityRef` (required)
- `evidence` (array): Up to 10 pointers to observations behind the claim; marks it grounded
- `expectedUntil` (string): When a temporary state with no stated end (ill, away) should be over; not an end: the fact stays current
- `object` (string, required)
- `predicate` (string, required)
- `sourceVertical` (string, required): Vertical name attributed as source (e.g. "rent")
- `userId` (string): Per-user scope: the fact (and a vertical+id entity) belongs to this user only
- `validFrom` (string, required)
- `validUntil` (string)

### `link_entities` (~194 tokens)

Declare a typed edge between two 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.

Input parameters:

- `from` (required)
- `kind` (string, required): Edge type (identity_of | paid_for | mentioned_in | worked_with | …)
- `sourceVertical` (string, required): Vertical attributed as source (e.g. "rent")
- `to` (required)
- `weight` (number)

### `retract_fact` (~113 tokens)

Retract a fact

Mark a fact as no longer believed. Cascades to facts derived from this one. Does not delete; the row remains for audit.

Input parameters:

- `factId` (string, required)
- `reason` (string, required)
- `retractedBy` (object): Who initiated the retraction — mirrors the REST RetractFactDto. Omit for the pre-existing default ({source: 'system'}); pass {source: 'human', userId} when relaying an operator/user decision so the a…

### `record_procedure` (~162 tokens)

Record a procedural memory (behaviour rule)

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.

Input parameters:

- `action` (string, required)
- `decayHalfLifeDays` (integer)
- `priority` (integer)
- `sourceKind` (string): Audit tag for who recorded this — default operator
- `trigger` (string, required)

### `retire_procedure` (~70 tokens)

Soft-retire a procedural memory entry

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.

Input parameters:

- `procedureId` (string, required): procedural_memory:<tail> or just the tail

### `record_decision` (~257 tokens)

Record a code-memory decision / rationale / invariant / gotcha

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.

Input parameters:

- `commit` (string): Commit SHA this was decided in (provenance)
- `confidence` (number)
- `kind` (string, required): decided = a design decision (supersedes prior); because = rationale; invariant = a constraint that must hold (supersedes prior); gotcha = a non-obvious trap (accumulates)
- `location` (string): file:line provenance, e.g. src/x.ts:42
- `symbol` (string, required): Code anchor — SCIP-style symbol or file path
- `text` (string, required): The decision / rationale / invariant / gotcha text
- `validFrom` (string): When the decision took effect — defaults to now

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/inite-ai-inite-brain-service/brain#diagnostics

## Score history

- 2026-11-05: 85
- 2026-11-04: 85
- 2026-11-03: 84
- 2026-11-02: 84
- 2026-11-01: 83
- 2026-10-31: 83
- 2026-10-30: 82
- 2026-10-29: 82
- 2026-10-28: 81
- 2026-10-27: 81
- 2026-10-26: 81
- 2026-10-25: 80
- 2026-10-24: 80
- 2026-10-23: 79
- 2026-10-22: 79
- 2026-10-21: 78
- 2026-10-20: 78
- 2026-10-19: 77
- 2026-10-18: 77
- 2026-10-17: 76
- 2026-10-16: 76

## Common questions

### What is the INITE Brain MCP server?

INITE Brain is an MCP server listed in the public MCP registry as io.github.inite-ai/inite-brain-service. Long-term memory for AI agents: a bitemporal knowledge graph with cited answers. This page covers its hosted endpoint (https://brain.inite.ai/mcp).

### Is the INITE Brain MCP server safe to use?

INITE Brain scores 85 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the INITE Brain MCP server expose?

INITE Brain exposes 30 tools: about_brain, how_to_connect, search_knowledge, search_multi_hop, graph_retrieve, and 25 more. Their descriptions and schemas cost roughly 5,018 tokens of context every time the server is loaded.

### Does the INITE Brain MCP server require authentication?

Yes. INITE Brain asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the INITE Brain MCP server still maintained?

INITE Brain is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://brain.inite.ai/mcp
- Repository: https://github.com/inite-ai/inite-brain-service
- Website: https://brain.inite.ai/
- Changelog RSS feed: https://verifymcp.io/servers/inite-ai-inite-brain-service/brain.xml
- Changelog JSON feed: https://verifymcp.io/servers/inite-ai-inite-brain-service/brain.json
- HTML version of this page: https://verifymcp.io/servers/inite-ai-inite-brain-service/brain