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

Est-ce que io.github.inite-ai/inite-brain-service est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.inite-ai/inite-brain-service » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 30 outils

• about_brain≈ 86 tokens

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

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "about_brain", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• detect_contradiction≈ 504 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 wouldOutcome ∈ {INSERTED, SUPERSEDED, COMPETING, REJECTED}; reasoning explains which rule fired (semantics class, score gap vs margin, cosine threshold, etc); opposingFacts lists the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.

  Paramètres, retour & exemple (8)

  Paramètres

  • object · string · requis
  • userId · string · optionnel
    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)
  • entityRef · ? · requis
  • predicate · string · requis
  • validFrom · string · requis
  • confidence · number · optionnel
  • validUntil · string · optionnel
  • sourceVertical · string · requis
    Vertical attributed as source (matches record_fact)

  Exemple d'appel

  {"name": "detect_contradiction", "arguments": {"object": "texte", "entityRef": "texte", "predicate": "texte", "validFrom": "texte", "sourceVertical": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• find_entity_communities≈ 149 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • entityId · string · requis
    knowledge_entity id

  Exemple d'appel

  {"name": "find_entity_communities", "arguments": {"entityId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• find_related_entities≈ 220 tokens

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

  Paramètres, retour & exemple (4)

  Paramètres

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

  Exemple d'appel

  {"name": "find_related_entities", "arguments": {"entityId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_competing_facts≈ 348 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 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.

  Paramètres, retour & exemple (4)

  Paramètres

  • asOf · string · optionnel
    Show what was competing at this ISO 8601 moment
  • userId · string · optionnel
    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)
  • entityId · string · requis
    Brain entity id (knowledge_entity:...) or short id
  • predicate · string · optionnel
    Filter to one predicate (e.g. "status", "address")

  Exemple d'appel

  {"name": "get_competing_facts", "arguments": {"entityId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_entity_profile≈ 234 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.

  Paramètres, retour & exemple (3)

  Paramètres

  • asOf · string · optionnel
    Valid-time as-of: facts true at this ISO 8601 moment (not a knowledge snapshot)
  • userId · string · optionnel
    Per-user memory scope: results include tenant-global facts plus this user's personal ones; omit for tenant-global only (fail-closed)
  • entityId · string · requis
    Brain entity id (knowledge_entity:...) or short id

  Exemple d'appel

  {"name": "get_entity_profile", "arguments": {"entityId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_entity_timeline≈ 190 tokens

  Chronological audit of all facts brain has learned about this entity, including retracted ones. Useful for "what did we know when" investigations.

  Paramètres, retour & exemple (4)

  Paramètres

  • since · string · optionnel
  • until · string · optionnel
  • userId · string · optionnel
    Per-user memory scope: results include tenant-global facts plus this user's personal ones; omit for tenant-global only (fail-closed)
  • entityId · string · requis

  Exemple d'appel

  {"name": "get_entity_timeline", "arguments": {"entityId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_fact≈ 241 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 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • factId · string · requis
    Fact id (knowledge_fact:...) or short id

  Exemple d'appel

  {"name": "get_fact", "arguments": {"factId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_fact_provenance≈ 250 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 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • factId · string · requis
    Fact id (knowledge_fact:...) or short id

  Exemple d'appel

  {"name": "get_fact_provenance", "arguments": {"factId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_source_reputation≈ 243 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 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • sourceKey · string · requis
    Source key, e.g. "rent:tenant_bot" or "code:_"

  Exemple d'appel

  {"name": "get_source_reputation", "arguments": {"sourceKey": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• graph_retrieve≈ 352 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" — the answer lives on a neighbour, not on Acme itself). Seeds score 1.0, neighbours 0.7; soft-fails to an empty result.

  Paramètres, retour & exemple (4)

  Paramètres

  • asOf · string · optionnel
    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)
  • query · string · optionnel
    Free-text fallback used to resolve seeds when a name does not match exactly
  • entityNames · array · requis
    Canonical names of the entities to anchor on
  • predicateHints · array · optionnel
    Prefer facts with these predicates (non-matching neighbour facts are dropped, seed facts kept at lower score)

  Exemple d'appel

  {"name": "graph_retrieve", "arguments": {"entityNames": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• how_to_connect≈ 115 tokens

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

  Paramètres, retour & exemple (1)

  Paramètres

  • client · string · optionnel
    Which client you are configuring, if you want the specific instructions.

  Exemple d'appel

  {"name": "how_to_connect", "arguments": {"client": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• link_entities≈ 419 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. 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.

  Paramètres, retour & exemple (5)

  Paramètres

  • to · ? · requis
  • from · ? · requis
  • kind · string · requis
    Edge type (identity_of | paid_for | mentioned_in | worked_with | …)
  • weight · number · optionnel
  • sourceVertical · string · requis
    Vertical attributed as source (e.g. "rent")

  Exemple d'appel

  {"name": "link_entities", "arguments": {"to": "texte", "from": "texte", "kind": "texte", "sourceVertical": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_communities≈ 118 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • limit · integer · optionnel

  Exemple d'appel

  {"name": "list_communities", "arguments": {"limit": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_procedures≈ 129 tokens

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

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
  • includeRetired · boolean · optionnel

  Exemple d'appel

  {"name": "list_procedures", "arguments": {"limit": 1, "includeRetired": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• match_procedure≈ 244 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 platinum tier; they get 20% off". Procedural memory is the third tier alongside facts (semantic) and episodes (timeline).

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
  • query · string · requis
    Natural-language context
  • minSimilarity · number · optionnel
    Floor (default 0.4); rows below are dropped

  Exemple d'appel

  {"name": "match_procedure", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• memory_diff≈ 415 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 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.

  Paramètres, retour & exemple (5)

  Paramètres

  • to · string · requis
    Exclusive upper bound (ISO 8601)
  • from · string · requis
    Inclusive lower bound (ISO 8601)
  • userId · string · optionnel
    Per-user memory scope: results include tenant-global facts plus this user's personal ones; omit for tenant-global only (fail-closed)
  • entityIds · array · optionnel
    Scope to these entities (short or full ids)
  • predicates · array · optionnel
    Scope to these predicates

  Exemple d'appel

  {"name": "memory_diff", "arguments": {"to": "texte", "from": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• recall_decisions≈ 186 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.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
  • query · string · requis
    Natural-language topic to recall the "why" for

  Exemple d'appel

  {"name": "recall_decisions", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• record_decision≈ 419 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` for the same anchor SUPERSEDES the prior one (decision evolution over time), while `because` / `gotcha` accumulate. Attach commit / location for provenance.

  Paramètres, retour & exemple (7)

  Paramètres

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

  Exemple d'appel

  {"name": "record_decision", "arguments": {"kind": "decided", "text": "texte", "symbol": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• record_fact≈ 604 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.

  Paramètres, retour & exemple (11)

  Paramètres

  • object · string · requis
  • userId · string · optionnel
    Per-user memory scope: the fact (and, for a vertical+id entityRef, the entity) belongs to this end-user only — invisible to other users and to requests that don't assert the same userId
  • evidence · array · optionnel
    Supporting observations behind the claim (≤10 typed pointers) — stored verbatim in the fact source; their presence marks the fact grounded (claim-grounding plane)
  • entityRef · ? · requis
  • predicate · string · requis
  • validFrom · string · requis
  • confidence · number · optionnel
  • validUntil · string · optionnel
  • expectedUntil · string · optionnel
    For a temporary state with no stated end (ill, travelling, away): when it should be over. Not an end — the fact stays current; answers say it was expected to be over once this passes
  • conversationId · string · optionnel
    Conversation this fact was observed in — names an observation, so the fact counts as grounded (claim-grounding plane)
  • sourceVertical · string · requis
    Vertical name attributed as source (e.g. "rent")

  Exemple d'appel

  {"name": "record_fact", "arguments": {"object": "texte", "entityRef": "texte", "predicate": "texte", "validFrom": "texte", "sourceVertical": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• record_procedure≈ 296 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 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.

  Paramètres, retour & exemple (5)

  Paramètres

  • action · string · requis
  • trigger · string · requis
  • priority · integer · optionnel
  • sourceKind · string · optionnel · operator | agent | dreams_loop
    Audit tag for who recorded this — default operator
  • decayHalfLifeDays · integer · optionnel

  Exemple d'appel

  {"name": "record_procedure", "arguments": {"action": "texte", "trigger": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• retire_procedure≈ 158 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.

  Paramètres, retour & exemple (1)

  Paramètres

  • procedureId · string · requis
    procedural_memory:<tail> or just the tail

  Exemple d'appel

  {"name": "retire_procedure", "arguments": {"procedureId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• retract_fact≈ 228 tokens

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

  Paramètres, retour & exemple (3)

  Paramètres

  • factId · string · requis
  • reason · string · requis
  • retractedBy · object · optionnel
    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 audit trail records the real initiator

  Exemple d'appel

  {"name": "retract_fact", "arguments": {"factId": "texte", "reason": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_communities≈ 257 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 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.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
  • query · string · requis
    Natural-language topic / domain
  • minSimilarity · number · optionnel
    Floor (default 0.3); rows below are dropped

  Exemple d'appel

  {"name": "search_communities", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_knowledge≈ 342 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 workspace.

  Paramètres, retour & exemple (6)

  Paramètres

  • asOf · string · optionnel
    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)
  • limit · integer · optionnel
    Max results (default 10)
  • query · string · requis
    Natural-language query
  • userId · string · optionnel
    Per-user memory scope: results include tenant-global facts plus this user's personal ones; omit for tenant-global only (fail-closed)
  • predicates · array · optionnel
    Filter to these predicates only
  • minConfidence · number · optionnel

  Exemple d'appel

  {"name": "search_knowledge", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_multi_hop≈ 530 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 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 finalEntityIds + supportingFactIds (HotpotQA-style evidence chain) so the caller can audit which facts drove the answer. Embedding model on this tenant: set per workspace.

  Paramètres, retour & exemple (8)

  Paramètres

  • asOf · string · optionnel
    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)
  • limit · integer · optionnel
  • query · string · requis
    Natural-language query
  • userId · string · optionnel
    Per-user memory scope: tenant-global plus this user's personal facts; omit for tenant-global only
  • maxHops · integer · optionnel
    Hard cap on planner hops (default 3, capped at 5 — beyond that latency dominates)
  • predicates · array · optionnel
    Filter to these predicates only
  • synthesize · boolean · optionnel
    Run the synthesizer over the final entity set and return a grounded answer with citations
  • synthesisGuardrails · string · optionnel · strict | lenient | off
    Override guardrails when synthesize=true: strict closes to null on partial; lenient returns the answer with the verifier verdict; off skips the verifier

  Exemple d'appel

  {"name": "search_multi_hop", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• summarize_entity≈ 453 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. 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.

  Paramètres, retour & exemple (4)

  Paramètres

  • asOf · string · optionnel
    Summarize what was known at this ISO 8601 moment
  • userId · string · optionnel
    Per-user memory scope: results include tenant-global facts plus this user's personal ones; omit for tenant-global only (fail-closed)
  • entityId · string · requis
    Brain entity id (knowledge_entity:...) or short id
  • styleHint · string · optionnel · neutral | sales | support | client_llm
    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)

  Exemple d'appel

  {"name": "summarize_entity", "arguments": {"entityId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• synthesize≈ 403 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 (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.

  Paramètres, retour & exemple (7)

  Paramètres

  • asOf · string · optionnel
    Valid-time as-of: facts true at this ISO 8601 moment (not a knowledge snapshot)
  • limit · integer · optionnel
    Top-K facts fed to the generator (default 10)
  • query · string · requis
    Natural-language question
  • userId · string · optionnel
    Per-user memory scope: tenant-global plus this user's personal facts; omit for tenant-global only
  • predicates · array · optionnel
  • minConfidence · number · optionnel
  • synthesisGuardrails · string · optionnel · strict | lenient | off
    Guardrail mode (default = SYNTHESIZE_DEFAULT_GUARDRAILS env)

  Exemple d'appel

  {"name": "synthesize", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• why≈ 270 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 was known at a past instant (bitemporal). Returns found:0 with empty memory when nothing is recorded.

  Paramètres, retour & exemple (3)

  Paramètres

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

  Exemple d'appel

  {"name": "why", "arguments": {"symbol": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• workspace_status≈ 243 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.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.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "workspace_status", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://brain.inite.ai/mcp