MCPサーバー

VaultCrux Memory Core

            io.github.CueCrux/vaultcrux-memory-core
        

ナレッジ・ドキュメント MCP・エージェント基盤公開・接続可能 MCP 2025-11-25

このMCPでできること

Stores and evaluates agent memory, facts, decisions, constraints, expertise, checkpoints, contradictions, and delegation readiness for evidence-based agent operation.

admit_character_kernel_entry

Admit Character Kernel Entry

Privileged curation tool for MemoryCrux v2.4 AgentCharacterKernel. Adds or supersedes an invariant expected behaviour tuple for an agent; operator-class API credentials are required by the API.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['agent_id', 'situation_fingerprint', 'expected_behavior', 'rationale'], 'properties': {'agent_id': {'type': 'string', 'minLength': 1}, 'rationale': {'type': 'string', 'minLength': 1}, 'supersedes_id': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}, 'expected_behavior': {'type': 'object', 'properties': {'tool': {'type': 'string', 'minLength': 1}, 'minSufficiency': {'type': 'number', 'maximum': 1, 'minimum': 0}}, 'additionalProperties': {}}, 'situation_fingerprint': {'type': 'string', 'pattern': '^[a-fA-F0-9]{64}$'}, 'expected_sufficiency_max': {'anyOf': [{'type': 'number', 'maximum': 1, 'minimum': 0}, {'type': 'null'}]}, 'expected_sufficiency_min': {'anyOf': [{'type': 'number', 'maximum': 1, 'minimum': 0}, {'type': 'null'}]}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

answer_elicitation

Answer Elicitation

Submit an answer to an elicitation question. Triggers coverage re-assessment, follow-up question selection, and automatic output routing to appropriate record types (operating rhythms, constraints, decision context, operator profile). Returns the next question or session completion.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id', 'question_id', 'answer'], 'properties': {'answer': {'anyOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}}, {'type': 'number'}]}, 'session_id': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}, 'question_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

assess_answerability

Assess Answerability

Sufficiency gate — can this question be answered with current evidence? Pass your query and optionally the fact rows you have gathered. Returns: answerable (yes/no), missing fields, contradictory fields, recommended next tool, and confidence. Use this BEFORE forcing a best-guess answer. If answerable=false, it is better to say 'insufficient evidence' than to guess wrong.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'query': {'type': 'string', 'minLength': 1}, 'candidate_rows': {'type': 'array', 'items': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

assess_character_drift

Assess Character Drift

Run the on-demand AgentCharacterKernel distribution-layer sweep for an agent and return emitted drift events for the requested window.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'minLength': 1}, 'window_end': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'window_start': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'min_decision_count': {'type': 'integer', 'maximum': 100000, 'minimum': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

assess_coverage

Assess Coverage

Question-scoped readiness check. Given a task description, returns what the system knows and doesn't know: artefact counts by domain, freshness stats, and knowledge gaps. Use BEFORE answering to decide if you should search more or commit. If coverage is thin on the question's topic, search with different terms before answering. Addresses 'do I have enough evidence to answer this?'

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['task_description'], 'properties': {'domains': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}}, 'action_types': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}}, 'task_description': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

assess_delegation_readiness

Assess Delegation Readiness

Multi-dimensional delegation readiness assessment. Checks operator profile completeness, operating rhythm coverage, constraint coverage, knowledge coverage, and decision framework coverage relative to the task. Returns overall readiness signal (ready/likely_ready/needs_work/not_ready), dimension-level gaps, and prioritised recommended actions. This is the pre-flight check for delegation, not for action (that's verify_before_acting).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['task_description'], 'properties': {'operator_id': {'type': 'string', 'minLength': 1}, 'task_description': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

build_timeline

Build Timeline

Deterministic timeline constructor for temporal reasoning. Finds all dated events matching your query, normalizes dates, and returns them sorted chronologically. Use for 'what order', 'before/after', 'earliest/latest' questions. Returns unresolved events (found but no date) separately.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'as_of': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'query': {'type': 'string', 'minLength': 1}, 'relation': {'enum': ['before', 'after', 'between', 'latest'], 'type': 'string'}, 'anchor_event': {'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

check_claim

Check Claim

Verify a proposed answer against memory before committing to it. Pass your candidate answer as claim_text. Returns supporting and contradicting evidence with confidence scores. Use as a pre-answer gate: if contradicting evidence exists or support is weak, investigate further before answering.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['claim_text'], 'properties': {'limit': {'type': 'integer', 'maximum': 10, 'minimum': 1}, 'agent_id': {'type': 'string', 'minLength': 1}, 'claim_text': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['verdict', 'confidence', 'matches'], 'properties': {'matches': {'type': 'array', 'items': {'type': 'object', 'required': ['chunkId', 'docId', 'title', 'url', 'content', 'score', 'confidence', 'sourcePlatform', 'sourceConversationId', 'version', 'topic', 'sourceTimestamp', 'freshnessScore'], 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'docId': {'type': 'string'}, 'score': {'type': 'number'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'topic': {'type': 'string', 'minLength': 1}, 'chunkId': {'type': 'string'}, 'content': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'version': {'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'freshnessScore': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'sourcePlatform': {'enum': ['openai', 'claude', 'gmail', 'slack', 'browser', 'manual', 'ob1'], 'type': 'string'}, 'sourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'sourceConversationId': {'type': 'string'}}, 'additionalProperties': False}}, 'verdict': {'enum': ['supported', 'insufficient', 'mixed'], 'type': 'string'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}}, 'additionalProperties': False}

check_constraints

Check Constraints

Check an action against all active constraints. Returns matched constraints, match types (structural/semantic), and a combined verdict (pass/warn/block).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['action_description'], 'properties': {'team_id': {'type': 'string', 'minLength': 1}, 'metadata': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'target_resources': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}}, 'action_description': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

check_deploy_readiness

Check Deploy Readiness

Is it safe to deploy these changes? Cross-references your changed modules against active constraints, recent incidents, knowledge freshness, and active alerts. Returns a composite verdict (ready/caution/block) with per-module breakdown and actionable recommendations. Use BEFORE deploying to catch constraint violations, recent regressions in the same area, stale knowledge that needs verification, and active alerts that might interact with your changes.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['changed_modules'], 'properties': {'changed_files': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'description': 'Specific files changed (for constraint matching)'}, 'deploy_target': {'type': 'string', 'description': "Deploy target environment (default 'production')"}, 'changed_modules': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'minItems': 1, 'description': "Modules being deployed (e.g. ['Engine', 'VaultCrux'])"}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

checkpoint_decision_state

Checkpoint Decision State

Create a receipted snapshot of your current decision state during a long-running session. Records decisions made, assumptions in effect, and open questions. Enables resumption by the same or different agent from the last checkpoint rather than replaying from zero.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id', 'summary'], 'properties': {'summary': {'type': 'string', 'minLength': 1}, 'session_id': {'type': 'string', 'minLength': 1}, 'open_questions': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}}, 'decisions_so_far': {'type': 'array', 'items': {'type': 'object', 'required': ['decision_id', 'description', 'outcome'], 'properties': {'outcome': {'type': 'string', 'minLength': 1}, 'decision_id': {'type': 'string', 'minLength': 1}, 'description': {'type': 'string', 'minLength': 1}}}}, 'assumptions_in_effect': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

compare_versions

Compare Versions

Temporal-ordered view of all values recorded for an (entity, predicate) pair, with the most-recent-before-as_of flagged as current. Use this when the agent sees contradictory facts ('Rachel moved to Chicago' AND 'Rachel moved to the suburbs') and needs to know which is current. Example calls: {entity:'user', predicate:'mortgage_amount'} returns every mortgage figure you've recorded, current first. {entity:'user', predicate:'family_trip_destination'} resolves the latest family-trip destination across sessions. {entity:'user', predicate:'previous_occupation'} returns the user's earlier roles when they changed jobs. Returns current_value directly plus has_multiple_versions so the caller can signal uncertainty, and may also include a cached narrative summary when FEATURE_CAUSAL_NARRATIVES is enabled.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['entity', 'predicate'], 'properties': {'entity': {'type': 'string', 'minLength': 1}, 'predicate': {'type': 'string', 'minLength': 1}, 'as_of_current': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

declare_available_models

Declare Available Models

Declare which models are available in this session for orchestration routing. Called once at session start.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id', 'models'], 'properties': {'models': {'type': 'array', 'items': {'type': 'object', 'required': ['name', 'capability_class', 'latency_tier'], 'properties': {'name': {'type': 'string'}, 'latency_tier': {'enum': ['low', 'medium', 'high'], 'type': 'string'}, 'capability_class': {'enum': ['fast', 'balanced', 'capable'], 'type': 'string'}}}, 'minItems': 1}, 'session_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

declare_constraint

Declare Constraint

Declare an organisational constraint (boundary, relationship, policy, or context flag) that agents must respect. This is a mutation operation.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['constraint_type', 'assertion'], 'properties': {'scope': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'team_id': {'type': 'string', 'minLength': 1}, 'evidence': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'severity': {'enum': ['critical', 'high', 'medium', 'low'], 'type': 'string'}, 'assertion': {'type': 'string', 'minLength': 1}, 'expires_at': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'constraint_type': {'enum': ['boundary', 'relationship', 'policy', 'context_flag'], 'type': 'string'}, 'assertion_structured': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'review_interval_days': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

decompose_expertise

Decompose Expertise

Decompose a high-level task class (e.g. 'handle marketing', 'review contracts') into specific steps with knowledge requirements, judgment requirements, delegation difficulty (trivial/moderate/hard/expert_only), existing coverage, and elicitation signals. Identifies which steps can be immediately delegated, which need elicitation first, and which are genuinely expert-only.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['task_class'], 'properties': {'depth': {'enum': ['overview', 'detailed'], 'type': 'string', 'default': 'overview'}, 'task_class': {'type': 'string', 'minLength': 1}, 'operator_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

derive_from_facts

Derive From Facts

Safe math and selection over a fact row set. Operations: sum, count, difference, max, min, latest, earliest. Pass the rows from enumerate_memory_facts and get a deterministic result with a computation trace. Removes arithmetic slop from totals, comparisons, and 'which is highest' questions.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['operation', 'rows'], 'properties': {'rows': {'type': 'array', 'items': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'minItems': 1}, 'operation': {'enum': ['sum', 'count', 'difference', 'max', 'min', 'latest', 'earliest'], 'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

dismiss_skill

Dismiss Skill

Dismiss a pending or quarantined skill submission. The skill is marked as dismissed and will not be promoted.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['submission_id', 'reason'], 'properties': {'notes': {'type': 'string', 'description': 'Additional notes'}, 'reason': {'type': 'string', 'minLength': 1, 'description': 'Reason for dismissal'}, 'submission_id': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$', 'description': 'ID of the skill submission to dismiss'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

enumerate_memory_facts

Enumerate Memory Facts

Deterministic fact-table extraction for aggregation questions and curated ESI lookups. Returns a structured row set (subject, predicate, object, date, session_id, confidence) instead of prose. Use this for 'how many', 'total', 'list all' questions — count the rows instead of hoping the LLM enumerates correctly. For curated ESI facts, pass `predicate` and optional `projectionVersionTag`; then `query` is optional and the server performs an exact predicate lookup without text search. Includes missing_dimensions to flag what might not have been found. Pass `mode: "aggregation"` (with `FEATURE_AGGREGATION_PREDICATE_EXPANSION=true` on the server) to enable: synonym expansion for pickup/return/acquire verbs, category-broadened counts from entity_categories, entity_type filters (expected_entity_types), and per-object dedup (dedup_by_object).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'mode': {'enum': ['standard', 'aggregation'], 'type': 'string'}, 'as_of': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'limit': {'type': 'integer', 'maximum': 200, 'minimum': 1}, 'query': {'type': 'string', 'minLength': 1}, 'category': {'type': 'string'}, 'predicate': {'type': 'string', 'minLength': 1}, 'predicates': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'minItems': 1}, 'subject_match': {'type': 'string', 'minLength': 1}, 'dedup_by_object': {'type': 'boolean'}, 'expand_synonyms': {'type': 'boolean'}, 'projectionVersionTag': {'type': 'string', 'minLength': 1}, 'dedup_by_subject_root': {'type': 'boolean'}, 'expected_entity_types': {'type': 'array', 'items': {'type': 'string'}}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

escalate_with_context

Escalate With Context

Contextual escalation — packages your full reasoning state (evidence gathered, options considered, recommended action) and routes to a human for review. Preserves work so the human responds with full context, not from scratch. Use when you hit genuine uncertainty that the system cannot evaluate.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['question', 'recommended_action', 'reasoning'], 'properties': {'urgency': {'enum': ['blocking', 'advisory'], 'type': 'string'}, 'question': {'type': 'string', 'minLength': 1}, 'reasoning': {'type': 'string', 'minLength': 1}, 'session_id': {'type': 'string', 'minLength': 1}, 'evidence_gathered': {'type': 'array', 'items': {'type': 'object', 'required': ['source_id', 'summary'], 'properties': {'summary': {'type': 'string', 'minLength': 1}, 'source_id': {'type': 'string', 'minLength': 1}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}}}}, 'options_considered': {'type': 'array', 'items': {'type': 'object', 'required': ['option'], 'properties': {'cons': {'type': 'array', 'items': {'type': 'string'}}, 'pros': {'type': 'array', 'items': {'type': 'string'}}, 'option': {'type': 'string', 'minLength': 1}, 'estimated_risk': {'enum': ['high', 'medium', 'low'], 'type': 'string'}}}}, 'recommended_action': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

expand_hit_context

Expand Hit Context

Session-neighborhood expansion around promising retrieval hits. When you find a relevant chunk but the specific fact (name, date, amount) is in a nearby turn, use this to fetch ±N turns from the same session. Recovers facts like 'my parents', '$6', or 'Disney+' that are near but not in the retrieved chunk.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['hit_ids'], 'properties': {'mode': {'enum': ['turn', 'session', 'window'], 'type': 'string'}, 'hit_ids': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'maxItems': 10, 'minItems': 1}, 'radius_turns': {'type': 'integer', 'maximum': 5, 'minimum': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

extract_facts_from_sessions

Extract Facts From Sessions

Scan the tenant's seeded sessions with rule-based extractors (money, counts, dates, project-role, acquire, version-chain) and emit structured facts to the projection stream so they become queryable via enumerate_memory_facts. Use when enumerate_memory_facts returns insufficient rows for aggregation, version-chain, or money questions and you suspect the fact exists but was under-predicated at ingest. Idempotent — safe to re-run (duplicate fact_hashes skipped unless overwrite_existing=true). Profile 'comprehensive' runs all rule families; narrower profiles ('money', 'counts', 'dates', 'version_chains') target a single family. Returns facts_added + rules_matched + receipt_id. Gated by FACT_EXTRACTION_MODE on the server.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'session_ids': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}}, 'extraction_profile': {'enum': ['comprehensive', 'money', 'counts', 'dates', 'version_chains'], 'type': 'string'}, 'overwrite_existing': {'type': 'boolean'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

fill_gap

Fill Knowledge Gap

Fill a previously reported gap with new knowledge. Gap must have been reported by a different tenant for cross-tenant credit.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['gap_receipt_id', 'content', 'evidence'], 'properties': {'content': {'type': 'string', 'minLength': 1}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['source_id', 'source_type'], 'properties': {'excerpt': {'type': 'string'}, 'source_id': {'type': 'string'}, 'source_type': {'type': 'string'}}}, 'minItems': 1}, 'gap_receipt_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_active_alerts

Get Active Alerts

Get active watch alerts across all watches for the tenant from the last 7 days.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_architecture_rationale

Get Architecture Rationale

Why is this module built this way? Aggregates all architectural decisions, active constraints, corrections, and skills for a domain into a coherent narrative. Use BEFORE refactoring or questioning a design choice — the answer is often 'it's that way because of compliance/performance/incident X'. Returns decisions sorted by recency, active constraints that still apply, and correction history showing what was tried and reverted.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['domain'], 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'Max results per category (default 30)'}, 'since': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$', 'description': 'How far back to search (ISO datetime, default 180 days)'}, 'domain': {'type': 'string', 'minLength': 1, 'description': "Domain or module to explain (e.g. 'retrieval', 'auth', 'billing', 'infra')"}, 'include': {'type': 'array', 'items': {'enum': ['decisions', 'constraints', 'corrections', 'skills', 'knowledge'], 'type': 'string'}, 'description': 'Which artefact types to include (default: all)'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_audit_trail

Get Audit Trail

Read VaultCrux Memory Core import audit history and linked receipt hashes for a topic.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['topic'], 'properties': {'limit': {'type': 'integer', 'maximum': 500, 'minimum': 1}, 'topic': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['topic', 'items'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object', 'required': ['memoryRecordId', 'versionId', 'docId', 'ingestJobId', 'sourcePlatform', 'sourceConversationId', 'version', 'status', 'sourceTimestamp', 'ingestedAt', 'contentHash', 'receiptId', 'receiptHash'], 'properties': {'docId': {'type': 'string'}, 'status': {'enum': ['queued', 'processed', 'failed', 'deduplicated'], 'type': 'string'}, 'version': {'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, 'receiptId': {'anyOf': [{'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}, {'type': 'null'}]}, 'versionId': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}, 'ingestedAt': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'contentHash': {'type': 'string', 'minLength': 1}, 'ingestJobId': {'anyOf': [{'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}, {'type': 'null'}]}, 'receiptHash': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'memoryRecordId': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}, 'sourcePlatform': {'enum': ['openai', 'claude', 'gmail', 'slack', 'browser', 'manual', 'ob1'], 'type': 'string'}, 'sourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'sourceConversationId': {'type': 'string'}}, 'additionalProperties': False}}, 'topic': {'type': 'string', 'minLength': 1}}, 'additionalProperties': False}

get_causal_chain

Get Causal Chain

Get the causal chain graph for a specific decision, showing how decisions, actions, and supersessions relate.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['decision_id'], 'properties': {'decision_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_character_kernel

Get Character Kernel

Return active AgentCharacterKernel entries for an agent, including expected behaviour tuples and sufficiency bands used by drift checks.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_checkpoints

Get Checkpoints

Retrieve decision checkpoints for a session. Returns the linked list of checkpoints in reverse chronological order. Use this to resume work from a prior checkpoint after session failure or handoff.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id'], 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1}, 'session_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_constraints

Get Constraints

List active organisational constraints, optionally filtered by type, status, or team.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 200, 'minimum': 1}, 'status': {'enum': ['active', 'suspended', 'superseded', 'expired'], 'type': 'string'}, 'team_id': {'type': 'string', 'minLength': 1}, 'constraint_type': {'enum': ['boundary', 'relationship', 'policy', 'context_flag'], 'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_contradictions

Get Contradictions

Find conflicting information across the user's memory. Returns groups of artefacts that contradict each other on the same topic. Use after gathering evidence for an answer — if your evidence sources disagree, this reveals which version is correct (typically the most recent).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 500, 'minimum': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['items'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object', 'required': ['topic', 'sourceCount', 'distinctContentCount', 'sourcePlatforms', 'latestSourceTimestamp'], 'properties': {'topic': {'type': 'string', 'minLength': 1}, 'sourceCount': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}, 'sourcePlatforms': {'type': 'array', 'items': {'enum': ['openai', 'claude', 'gmail', 'slack', 'browser', 'manual', 'ob1'], 'type': 'string'}}, 'distinctContentCount': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}, 'latestSourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}, 'additionalProperties': False}}}, 'additionalProperties': False}

get_correction_chain

Get Correction Chain

Trace how a fact or decision evolved over time. When you find a value (e.g. 'Rachel moved to Chicago'), call this to check if a more recent session supersedes it. Returns the full version chain with timestamps. ALWAYS use for 'current', 'now', 'most recent' questions before answering with the first value you find.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['decision_id'], 'properties': {'decision_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_decision_context

Get Decision Context

Retrieve agent session decisions from the CoreCrux Decision Plane, including decision IDs, outcomes, and cursor positions.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_decisions_on_stale_context

Get Decisions on Stale Context

Find decisions in a session that may have been made on stale memory context.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_domain_changelog

Domain Changelog

Cross-artefact-type changelog for specified domains since a given timestamp. Returns constraints added/updated, knowledge changes, decisions recorded, and alerts raised/resolved. Use at session start to learn what changed in your domain since your last session.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['domains', 'since'], 'properties': {'limit': {'type': 'integer', 'maximum': 500, 'minimum': 1, 'description': 'Maximum entries to return (default 500)'}, 'since': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$', 'description': 'Changelog start timestamp (max 90 days ago)'}, 'domains': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'minItems': 1, 'description': 'Domains to check for changes'}, 'include': {'type': 'array', 'items': {'enum': ['constraints', 'knowledge', 'decisions', 'alerts', 'skills'], 'type': 'string'}, 'description': 'Optional filter for artefact types'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_enrichment_status

Get Enrichment Status

Check the status of submitted corrections (pending, corroborated, merged, retracted, expired).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'default': 10, 'maximum': 50, 'minimum': 1}, 'status': {'enum': ['pending', 'corroborated', 'merged', 'retracted', 'expired'], 'type': 'string'}, 'correction_id': {'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_escalation_recommendation

Get Escalation Recommendation

Get model routing recommendation for a query based on composite confidence and difficulty profile. Returns escalation advice: none, recommended, or required.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'query': {'type': 'string', 'minLength': 1}, 'session_id': {'type': 'string'}, 'current_model': {'type': 'string'}, 'query_confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_freshness_report

Get Freshness Report

Check how recent the stored knowledge is across topics. Returns staleness indicators per topic. Use this when answering time-sensitive questions to verify your evidence isn't outdated. Topics with stale data may have been superseded by newer conversations not yet retrieved.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 500, 'minimum': 1}, 'stale_after_days': {'type': 'integer', 'maximum': 3650, 'minimum': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['items'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object', 'required': ['topic', 'latestSourceTimestamp', 'oldestSourceTimestamp', 'sourceCount', 'staleSourceCount', 'freshnessScore', 'stale'], 'properties': {'stale': {'type': 'boolean'}, 'topic': {'type': 'string', 'minLength': 1}, 'sourceCount': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}, 'freshnessScore': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'staleSourceCount': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}, 'latestSourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'oldestSourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}, 'additionalProperties': False}}}, 'additionalProperties': False}

get_incident_context

Get Incident Context

What went wrong last time we touched this module? Returns past incidents, deploy failures, gotchas, and active constraints for a module or system. Use BEFORE modifying infrastructure code, deploy scripts, or any module with a history of fragility. Surfaces the kind of tribal knowledge that prevents repeat failures — Docker bind mount traps, Vault agent write patterns, stale dist/ artifacts, port conflicts, and similar operational landmines.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['module'], 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1, 'description': 'Max results to return (default 20)'}, 'module': {'type': 'string', 'minLength': 1, 'description': "Module or system name (e.g. 'Engine', 'VaultCrux', 'docker', 'vault-agent')"}, 'days_back': {'type': 'integer', 'maximum': 365, 'minimum': 1, 'description': 'How many days back to search (default 90)'}, 'code_paths': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}, 'description': 'Specific code paths to check for related incidents'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_knowledge_gaps

Get Knowledge Gaps

List gap receipts (coverage + enumeration) for the tenant, filterable by topic and recency.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 100, 'minimum': 1}, 'since_days': {'type': 'integer', 'default': 30, 'maximum': 9007199254740991, 'minimum': 1}, 'gap_subtype': {'enum': ['coverage', 'enumeration'], 'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_my_tasks

My Tasks

Read-through to PlanCrux task graph. Returns tasks assigned to or relevant to the calling agent, filtered by status and priority. Includes stage progress, blockers, and linked MemoryCrux artefact counts.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1, 'description': 'Max tasks to return (default 10)'}, 'status': {'type': 'string', 'description': 'Filter by task status (e.g. incomplete, in_progress, testing)'}, 'priority': {'type': 'string', 'description': 'Filter by priority (critical, high, medium, low)'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_operating_rhythms

Get Operating Rhythms

Retrieve operating rhythm records for an operator — temporal behavioural patterns capturing what the human actually does (not what their calendar says). Filterable by cadence (daily, weekly, monthly) and delegation status. Returns structured sequences with delegation readiness signals.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'cadence': {'enum': ['daily', 'weekly', 'monthly', 'quarterly', 'event_triggered'], 'type': 'string'}, 'operator_id': {'type': 'string', 'minLength': 1}, 'delegation_status': {'enum': ['fully_delegatable', 'partially_delegatable', 'human_only'], 'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_operator_profile

Get Operator Profile

Retrieve the human operator's working context: role, domain expertise, communication preferences, quality bar, trusted/distrusted sources. Returns the latest version of the profile. Defaults to the operator linked to the calling agent's passport.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'operator_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_passport

Get Passport

Return the calling agent's passport with current reputation tier and receipt count. Recalculates receipt count on every call and auto-upgrades the tier when new thresholds are met (basic 10+, established 100+, trusted 500+, elite 2000+). Includes a hint for the next tier upgrade.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_platform_capabilities

Get Platform Capabilities

Machine-queryable manifest of all available MemoryCrux tools, required trust tiers, and credit costs. Returns structured data for agent-to-service evaluation without reading documentation. Free (0 credits) at all tiers — discovery drives adoption.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'category': {'type': 'string', 'minLength': 1}, 'min_trust_tier': {'type': 'string', 'minLength': 1}, 'max_credit_cost': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_pressure_status

Get Pressure Status

Get Engine knowledge pressure status for the tenant — indicates whether knowledge bases are under update pressure.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_relevant_context

Get Relevant Context

Task-scoped context briefing. Returns a prioritised context payload shaped by your task description, ranked by risk-if-missed. Constraints and alerts rank above general knowledge. Use at the START of reasoning about a question to get the system's best assessment of what's relevant. Complements query_memory: this gives breadth, query_memory gives depth.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['task_description', 'token_budget'], 'properties': {'token_budget': {'type': 'integer', 'maximum': 100000, 'minimum': 100}, 'priority_signal': {'enum': ['safety_first', 'completeness_first', 'recency_first'], 'type': 'string'}, 'task_description': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_session_dossiers

Get Session Dossiers

Retrieve pre-synthesized per-session memory dossiers (typed: experience | fact | preference; with When/Involving/To-purpose metadata). Use for multi-session or preference-style questions where stitching across conversations is the bottleneck — the dossier already summarises each session's key events. Two modes: mode='search' with a query (BM25-ish ranking over summary+purpose, optional type_filter), or mode='list' returns the tenant's most-recent dossiers chronologically. Tenants without FEATURE_SESSION_DOSSIERS enabled return an empty list (no error).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'mode': {'enum': ['search', 'list'], 'type': 'string'}, 'limit': {'type': 'integer', 'maximum': 200, 'minimum': 1}, 'query': {'type': 'string'}, 'type_filter': {'enum': ['experience', 'fact', 'preference'], 'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_signals_feed

Get Signals Feed

Get the signals feed for the tenant from the WebCrux platform.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 100, 'minimum': 1}, 'since': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_task_context

Task Context

Full task context: task metadata, stages with status and weight, active blockers, linked artefacts (constraints, decisions, knowledge), recent log entries, and pinned master plan version. Assembles the full picture from PlanCrux and MemoryCrux.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['task_id'], 'properties': {'task_id': {'type': 'string', 'minLength': 1, 'description': 'PlanCrux task ID or title'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

get_versioned_snapshot

Get Versioned Snapshot

Get the latest versioned snapshot for a VaultCrux Memory Core topic at an optional timestamp.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['topic'], 'properties': {'limit': {'type': 'integer', 'maximum': 500, 'minimum': 1}, 'topic': {'type': 'string', 'minLength': 1}, 'timestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['topic', 'at', 'items'], 'properties': {'at': {'anyOf': [{'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, {'type': 'null'}]}, 'items': {'type': 'array', 'items': {'type': 'object', 'required': ['memoryRecordId', 'versionId', 'docId', 'title', 'url', 'preview', 'sourcePlatform', 'sourceConversationId', 'version', 'topic', 'sourceTimestamp', 'freshnessScore'], 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'docId': {'type': 'string'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'topic': {'type': 'string', 'minLength': 1}, 'preview': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'version': {'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, 'versionId': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}, 'freshnessScore': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'memoryRecordId': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}, 'sourcePlatform': {'enum': ['openai', 'claude', 'gmail', 'slack', 'browser', 'manual', 'ob1'], 'type': 'string'}, 'sourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'sourceConversationId': {'type': 'string'}}, 'additionalProperties': False}}, 'topic': {'type': 'string', 'minLength': 1}}, 'additionalProperties': False}

investigate_question

Investigate Question

Composite server-side investigation tool. Pass a question and the server automatically: (1) detects intent (aggregation/temporal/ordering/knowledge-update/recall), (2) queries the entity index for structured facts, (3) builds a timeline for temporal questions, (4) retrieves memory chunks with the right scoring profile, (5) expands context around sparse hits, (6) derives counts/sums for aggregation, (7) assesses answerability, and (8) returns a recommendation. Use this as your FIRST tool for any non-trivial question — it does the multi-step investigation that would otherwise take 4-6 individual tool calls. The response includes structured facts, timeline, retrieved chunks, derived results, answerability assessment, and a recommendation for how to answer.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['question'], 'properties': {'question': {'type': 'string', 'minLength': 1}, 'question_date': {'type': 'string'}, 'scoring_profile': {'enum': ['balanced', 'recall', 'recency'], 'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

issue_passport

Issue Passport

Issue an agent passport with identity, sponsor lineage, and a 5-tier reputation system. Stored as a BLAKE3-hashed fact. Tiers: unverified (0), basic (10+ receipts), established (100+), trusted (500+), elite (2000+). Required before sync operations. Idempotent: calling twice returns the existing passport.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'sponsor_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

list_external_services

List External Services

List registered external services available to the calling agent. Returns service IDs, display names, allowed methods/paths, and rate limit state. Does not return credentials or credential references.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'status': {'enum': ['active', 'suspended'], 'type': 'string', 'description': 'Filter by service status'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

list_topics

List Topics

List VaultCrux Memory Core topic groups with freshness metadata.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 500, 'minimum': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['items'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object', 'required': ['topic', 'recordCount', 'sourceCount', 'latestSourceTimestamp', 'freshnessScore'], 'properties': {'topic': {'type': 'string', 'minLength': 1}, 'recordCount': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}, 'sourceCount': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}, 'freshnessScore': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'latestSourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}, 'additionalProperties': False}}}, 'additionalProperties': False}

log_progress

Log Progress

Receipted write-through to PlanCrux's log endpoint. Appends a structured log entry to a task with optional evidence references and stage binding. Cannot change task or stage status (human-only), but records work done, findings, and blockers encountered.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['task_id', 'note'], 'properties': {'note': {'type': 'string', 'minLength': 4, 'description': 'What was done'}, 'task_id': {'type': 'string', 'minLength': 1, 'description': 'PlanCrux task ID'}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'reference'], 'properties': {'type': {'enum': ['receipt', 'artefact', 'url', 'text'], 'type': 'string'}, 'reference': {'type': 'string', 'minLength': 1}}}, 'description': 'Evidence references for the log entry'}, 'stage_id': {'type': 'string', 'description': 'Bind this log to a specific stage'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

memory_claim_check

Memory Claim Check (paid)

agent-ux-04 paid-tier source-linked claim check. Same upstream API as check_claim, plus three additional gates: (1) token_budget is REQUIRED — caps total response size by per-match token estimate (QC.2); (2) reserved-prefix topics (__agent::*, __ops::*, __bootstrap__::*) are stripped from matches (T.1); (3) per-match audit_links carry an offline-verify CLI hint (`corecruxctl receipts verify <id>`) so the host IDE can render a one-click verify badge per supporting / contradicting memory. Gated by FEATURE_MEMORY_CLAIM_CHECK=1 (default off).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['claim_text', 'token_budget'], 'properties': {'top_k': {'type': 'integer', 'maximum': 10, 'minimum': 1}, 'agent_id': {'type': 'string', 'minLength': 1}, 'claim_text': {'type': 'string', 'minLength': 1}, 'token_budget': {'type': 'integer', 'maximum': 100000, 'minimum': 100}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['verdict', 'confidence', 'matches'], 'properties': {'matches': {'type': 'array', 'items': {'type': 'object', 'required': ['chunkId', 'docId', 'title', 'url', 'content', 'score', 'confidence', 'sourcePlatform', 'sourceConversationId', 'version', 'topic', 'sourceTimestamp', 'freshnessScore'], 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'docId': {'type': 'string'}, 'score': {'type': 'number'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'topic': {'type': 'string', 'minLength': 1}, 'chunkId': {'type': 'string'}, 'content': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'version': {'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'freshnessScore': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'sourcePlatform': {'enum': ['openai', 'claude', 'gmail', 'slack', 'browser', 'manual', 'ob1'], 'type': 'string'}, 'sourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'sourceConversationId': {'type': 'string'}}, 'additionalProperties': False}}, 'verdict': {'enum': ['supported', 'insufficient', 'mixed'], 'type': 'string'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}}, 'additionalProperties': False}

memory_freshness_report

Memory Freshness Report (paid alias)

Aligned with the Crux free-tier `memory_freshness` surface. Same backend as get_freshness_report with a token_budget knob (QC.2). Gated by FEATURE_MEMORY_FRESHNESS_REPORT=1.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'limit': {'type': 'integer', 'maximum': 500, 'minimum': 1}, 'token_budget': {'type': 'integer', 'maximum': 20000, 'minimum': 1}, 'stale_after_days': {'type': 'integer', 'maximum': 3650, 'minimum': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['items'], 'properties': {'items': {'type': 'array', 'items': {'type': 'object', 'required': ['topic', 'latestSourceTimestamp', 'oldestSourceTimestamp', 'sourceCount', 'staleSourceCount', 'freshnessScore', 'stale'], 'properties': {'stale': {'type': 'boolean'}, 'topic': {'type': 'string', 'minLength': 1}, 'sourceCount': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}, 'freshnessScore': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'staleSourceCount': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': 0}, 'latestSourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'oldestSourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}, 'additionalProperties': False}}}, 'additionalProperties': False}

promote_skill

Promote Skill

Promote a reviewed skill submission to Engine artifacts, making it retrievable via get_relevant_context. Only pending_review skills can be promoted. Returns the promoted artifact ID.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['submission_id'], 'properties': {'visibility': {'type': 'string', 'description': 'Override target visibility'}, 'review_notes': {'type': 'string', 'description': 'Notes from the reviewer'}, 'submission_id': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$', 'description': 'ID of the skill submission to promote'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

provision_agent_context

Provision Agent Context

Generate a structured, receipted context package for a new agent — the equivalent of soul.md + heartbeat.md + user.md but machine-queryable and backed by MemoryCrux records. Includes identity, operator context, active constraints, operating rhythms, knowledge briefing, and heartbeat schedule. Scope: minimal (identity + constraints), standard (all), comprehensive (standard + full knowledge).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['agent_role'], 'properties': {'scope': {'enum': ['minimal', 'standard', 'comprehensive'], 'type': 'string', 'default': 'standard'}, 'agent_role': {'type': 'string', 'minLength': 1}, 'operator_id': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

query_memory

Query Memory

Search the user's conversation memory. Returns ranked results with content, source timestamps, and confidence scores. For KNOWLEDGE UPDATE questions ('current', 'now', 'most recent'): make two calls — one with scoring_profile='balanced' and one with scoring_profile='recency' — then use the value from the most recent source_timestamp. For COUNTING questions ('how many', 'total'): results may not be exhaustive — search with varied terms and enumerate explicitly before counting. If all results score below 0.3, reformulate with synonyms or specific entity names from the question.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'maximum': 50, 'minimum': 1}, 'query': {'type': 'string', 'minLength': 1}, 'topic': {'type': 'string', 'minLength': 1}, 'format': {'enum': ['raw', 'narrative'], 'type': 'string'}, 'date_to': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'agent_id': {'type': 'string', 'minLength': 1}, 'date_from': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'date_range': {'type': 'object', 'properties': {'to': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'from': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}, 'additionalProperties': False}, 'question_date': {'type': 'string', 'minLength': 1}, 'scoring_profile': {'enum': ['balanced', 'recall', 'recency', 'temporal', 'assistant_ref', 'vocabulary_gap', 'supersession', 'aggregation'], 'type': 'string'}, 'confidence_threshold': {'type': 'number', 'maximum': 1, 'minimum': 0}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['results'], 'properties': {'results': {'type': 'array', 'items': {'type': 'object', 'required': ['chunkId', 'docId', 'title', 'url', 'content', 'score', 'confidence', 'sourcePlatform', 'sourceConversationId', 'version', 'topic', 'sourceTimestamp', 'freshnessScore'], 'properties': {'url': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'docId': {'type': 'string'}, 'score': {'type': 'number'}, 'title': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'topic': {'type': 'string', 'minLength': 1}, 'chunkId': {'type': 'string'}, 'content': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}, 'version': {'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'freshnessScore': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'sourcePlatform': {'enum': ['openai', 'claude', 'gmail', 'slack', 'browser', 'manual', 'ob1'], 'type': 'string'}, 'sourceTimestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'sourceConversationId': {'type': 'string'}}, 'additionalProperties': False}}}, 'additionalProperties': False}

reconstruct_knowledge_state

Reconstruct Knowledge State

Reconstruct what the system knew at a specific point in time. Returns both current and superseded artefacts as of that timestamp. Use for temporal reasoning: 'what was true in January?' vs 'what is true now?' Compare two calls at different timestamps to see what changed.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['decision_id'], 'properties': {'decision_id': {'type': 'string', 'minLength': 1}, 'at_timestamp': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, 'include_superseded': {'type': 'boolean'}, 'include_confidence_landscape': {'type': 'boolean'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

record_decision_context

Record Decision Context

Record a decision context event in the CoreCrux Decision Plane. This is a mutation operation.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id', 'decision_id', 'context'], 'properties': {'context': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'agent_id': {'type': 'string', 'minLength': 1}, 'session_id': {'type': 'string', 'minLength': 1}, 'decision_id': {'type': 'string', 'minLength': 1}, 'occurred_at': {'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

register_external_service

Register an external service and store its credential via Vault Transit. Human-only (admin or owner role). The credential is encrypted immediately on receipt and never stored in plaintext. Returns the service registration record without the credential.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['service_id', 'display_name', 'base_url', 'auth_type', 'credential_value'], 'properties': {'base_url': {'type': 'string', 'format': 'uri', 'description': 'Service base URL (must be HTTPS)'}, 'auth_type': {'enum': ['api_key', 'bearer', 'oauth2_client_credentials'], 'type': 'string', 'description': 'Authentication type'}, 'rate_limit': {'type': 'object', 'properties': {'requests_per_day': {'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}, 'requests_per_minute': {'type': 'integer', 'maximum': 9007199254740991, 'exclusiveMinimum': 0}}, 'description': 'Rate limits for this service'}, 'service_id': {'type': 'string', 'minLength': 1, 'description': 'Tenant-unique identifier for the service'}, 'display_name': {'type': 'string', 'minLength': 1, 'description': 'Human-readable service name'}, 'allowed_paths': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Allowed path patterns (default: *)'}, 'auth_injection': {'type': 'object', 'required': ['location', 'key_name', 'value_template'], 'properties': {'key_name': {'type': 'string', 'minLength': 1}, 'location': {'enum': ['header', 'query'], 'type': 'string'}, 'value_template': {'type': 'string', 'minLength': 1}}, 'description': 'How to inject the credential into requests'}, 'allowed_methods': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Allowed HTTP methods (default: GET, POST)'}, 'credential_value': {'type': 'string', 'minLength': 1, 'description': 'The credential (encrypted immediately, never stored plaintext)'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

request_credentialed_call

Credentialed External Call

Proxied external API call with server-side credential injection. VaultCrux retrieves the credential from Vault Transit, injects it per the service's auth template, makes the call, and returns the response. The credential never appears in your context window. Request and response are receipted and audit-logged.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['service_id', 'method', 'path'], 'properties': {'path': {'type': 'string', 'minLength': 1, 'description': 'Request path (e.g. /v1/chat/completions)'}, 'method': {'enum': ['GET', 'POST', 'PUT', 'PATCH', 'DELETE'], 'type': 'string', 'description': 'HTTP method'}, 'headers': {'type': 'object', 'description': 'Additional headers (not auth)', 'propertyNames': {'type': 'string'}, 'additionalProperties': {'type': 'string'}}, 'payload': {'type': 'object', 'description': 'Request body for POST/PUT', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'service_id': {'type': 'string', 'minLength': 1, 'description': 'Registered service ID'}, 'session_id': {'type': 'string', 'description': 'Session ID for audit trail'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

retract_skill

Retract Skill

Retract a previously promoted skill. Sets the Engine artifact's living status to 'retracted', removing it from future retrieval results. Use when a skill is found to be incorrect or outdated.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['submission_id', 'reason'], 'properties': {'notes': {'type': 'string', 'description': 'Additional notes'}, 'reason': {'type': 'string', 'minLength': 1, 'description': 'Reason for retraction'}, 'submission_id': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$', 'description': 'ID of the skill submission to retract'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

run_elicitation

Run Elicitation

Start or resume a structured elicitation session for a specific knowledge layer. Layers: operating_rhythm, recurring_decisions, dependencies, friction, judgment_patterns, quality_standards, or 'full' for all layers. Returns the first question and session metadata. Use answer_elicitation to submit answers.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['layer'], 'properties': {'layer': {'enum': ['operating_rhythm', 'recurring_decisions', 'dependencies', 'friction', 'judgment_patterns', 'quality_standards', 'full'], 'type': 'string'}, 'operator_id': {'type': 'string', 'minLength': 1}, 'resume_from': {'type': 'string', 'format': 'uuid', 'pattern': '^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

session_debrief

Session Debrief

Structured session-end reflection. Routes discoveries to appropriate capture tools (suggest_constraint, submit_skill, flag_for_review). Produces a receipted debrief record. Call before closing any session longer than 10 minutes.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['session_id'], 'properties': {'session_id': {'type': 'string', 'minLength': 1, 'description': 'Session ID for the debrief'}, 'discoveries': {'type': 'array', 'items': {'type': 'object', 'required': ['finding', 'category', 'confidence', 'evidence'], 'properties': {'finding': {'type': 'string', 'minLength': 1}, 'category': {'enum': ['constraint', 'knowledge', 'skill', 'correction', 'gap'], 'type': 'string'}, 'evidence': {'type': 'string', 'minLength': 1}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}}}, 'default': [], 'description': 'Discoveries made during the session'}, 'suggested_actions': {'type': 'array', 'items': {'type': 'object', 'required': ['action', 'payload_summary'], 'properties': {'action': {'enum': ['suggest_constraint', 'submit_skill', 'flag_for_review'], 'type': 'string'}, 'payload_summary': {'type': 'string', 'minLength': 1}}}, 'default': [], 'description': 'Actions to route from session discoveries'}, 'assumptions_validated': {'type': 'array', 'items': {'type': 'object', 'required': ['assumption', 'validation_evidence'], 'properties': {'assumption': {'type': 'string', 'minLength': 1}, 'validation_evidence': {'type': 'string', 'minLength': 1}}}, 'default': [], 'description': 'Assumptions that were validated during the session'}, 'assumptions_invalidated': {'type': 'array', 'items': {'type': 'object', 'required': ['assumption', 'invalidation_evidence'], 'properties': {'assumption': {'type': 'string', 'minLength': 1}, 'invalidation_evidence': {'type': 'string', 'minLength': 1}, 'corrective_action_taken': {'anyOf': [{'type': 'string'}, {'type': 'null'}]}}}, 'default': [], 'description': 'Assumptions that were invalidated during the session'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

submit_correction

Submit Correction

Submit a correction for a knowledge item with evidence chain. The original item is never mutated — a versioned enrichment layer is created.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['original_item_id', 'correction_type', 'corrected_content', 'evidence'], 'properties': {'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['source_id', 'source_type'], 'properties': {'excerpt': {'type': 'string'}, 'source_id': {'type': 'string'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'source_type': {'type': 'string'}}}, 'minItems': 1}, 'correction_type': {'enum': ['stale_value', 'partial_data', 'factual_error', 'context_missing'], 'type': 'string'}, 'original_item_id': {'type': 'string', 'minLength': 1}, 'corrected_content': {'type': 'string', 'minLength': 1}, 'parent_receipt_id': {'type': 'string'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

submit_skill

Submit Skill

Submit a procedural workflow skill discovered during work. Pro+ private skills auto-approve; Starter skills enter a review queue. ATAM injection scanning runs automatically — quarantined skills cannot be promoted. Returns submission ID, approval status, and scan results.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['title', 'content'], 'properties': {'title': {'type': 'string', 'minLength': 1, 'description': 'Short title summarising the skill'}, 'run_id': {'type': 'string', 'description': 'AgentCrux run ID'}, 'content': {'type': 'string', 'minLength': 1, 'description': 'Full procedural skill content (markdown)'}, 'agent_role': {'type': 'string', 'description': 'Role of the submitting agent'}, 'session_id': {'type': 'string', 'description': 'Session ID for provenance tracking'}, 'skill_domains': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Knowledge domains this skill applies to'}, 'discovery_context': {'type': 'string', 'description': 'How/where the skill was discovered'}, 'target_visibility': {'enum': ['private', 'partner', 'public_proposed'], 'type': 'string', 'default': 'private', 'description': 'Visibility scope for the skill'}, 'skill_tool_references': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Tool names this skill references'}, 'supersedes_artifact_id': {'type': 'integer', 'maximum': 9007199254740991, 'minimum': -9007199254740991, 'description': 'Artifact ID this skill replaces'}, 'skill_trigger_description': {'type': 'string', 'description': 'When this skill should be activated'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

suggest_constraint

Suggest Constraint

Propose an organisational constraint discovered during work for human review. Agents can suggest boundaries, policies, or context flags they discover — humans decide whether to promote them to active constraints. Low barrier (1 credit); authority gate is on promotion, not suggestion.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['assertion', 'constraint_type'], 'properties': {'scope': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'evidence': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'severity': {'enum': ['critical', 'high', 'medium', 'low'], 'type': 'string'}, 'assertion': {'type': 'string', 'minLength': 1}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'session_id': {'type': 'string', 'minLength': 1}, 'constraint_type': {'enum': ['boundary', 'relationship', 'policy', 'context_flag'], 'type': 'string'}, 'discovery_context': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

sync_pull

Sync Pull

Pull enriched facts from a remote memory instance into the local fact store. Uses cursor-based pagination and resumes from the last pull cursor. Pulled facts carry a sync:source_receipt so they are never pushed back. Requires an agent passport with at least basic tier (10+ receipts).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'entity_prefix': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

sync_push

Sync Push

Push local facts to a remote memory instance. Private facts and sensitive entity prefixes (finance:, health:, credentials:, etc.) are never pushed. Call without confirm=true for a preview. Requires established passport tier (100+ receipts).

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'confirm': {'type': 'boolean'}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

update_constraint

Update Constraint

Update an existing constraint. Content changes create a new version (append-only). Status-only changes update in place. This is a mutation operation.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['constraint_id'], 'properties': {'scope': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'status': {'enum': ['active', 'suspended', 'superseded', 'expired'], 'type': 'string'}, 'evidence': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'severity': {'enum': ['critical', 'high', 'medium', 'low'], 'type': 'string'}, 'assertion': {'type': 'string', 'minLength': 1}, 'expires_at': {'anyOf': [{'type': 'string', 'format': 'date-time', 'pattern': '^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$'}, {'type': 'null'}]}, 'constraint_id': {'type': 'string', 'minLength': 1}, 'assertion_structured': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'review_interval_days': {'anyOf': [{'type': 'integer', 'maximum': 9007199254740991, 'minimum': 1}, {'type': 'null'}]}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

update_operator_profile

Update Operator Profile

Update the operator profile. Creates a new version with provenance receipt (does not mutate). Accepts partial updates — fields not provided are preserved from the previous version.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'operator_id': {'type': 'string', 'minLength': 1}, 'quality_bar': {'type': 'array', 'items': {'type': 'object', 'properties': {}, 'additionalProperties': {}}}, 'trusted_sources': {'type': 'array', 'items': {'type': 'object', 'properties': {}, 'additionalProperties': {}}}, 'domain_expertise': {'type': 'array', 'items': {'type': 'string'}}, 'experience_level': {'enum': ['junior', 'mid', 'senior', 'executive'], 'type': 'string'}, 'role_description': {'type': 'string', 'minLength': 1}, 'distrusted_sources': {'type': 'array', 'items': {'type': 'object', 'properties': {}, 'additionalProperties': {}}}, 'communication_preferences': {'type': 'object', 'properties': {}, 'additionalProperties': {}}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

verify_before_acting

Verify Before Acting

Pre-action and pre-conclusion verification gate. Checks Shield policy, org constraints, watch alerts, knowledge pressure, and memory freshness. Returns a combined verdict: proceed, warn, require_approval, or block. Use before committing to an answer when the stakes are high or when your evidence is thin — it catches constraint conflicts and stale-context risks that query_memory alone won't surface.

入力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['tool_name', 'action_description'], 'properties': {'team_id': {'type': 'string', 'minLength': 1}, 'metadata': {'type': 'object', 'propertyNames': {'type': 'string'}, 'additionalProperties': {}}, 'tool_name': {'type': 'string', 'minLength': 1}, 'is_mutation': {'type': 'boolean'}, 'publisher_id': {'type': 'string', 'minLength': 1}, 'server_digest': {'type': 'string', 'minLength': 1}, 'target_resources': {'type': 'array', 'items': {'type': 'string', 'minLength': 1}}, 'action_description': {'type': 'string', 'minLength': 1}}}

出力スキーマ

{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}, 'additionalProperties': False}

追加

                            decompose_expertise
                        

2026年9月17日12:41

追加

                            provision_agent_context
                        

2026年9月17日12:41

追加

                            assess_delegation_readiness
                        

2026年9月17日12:41

追加

                            get_operating_rhythms
                        

2026年9月17日12:41

追加

                            answer_elicitation
                        

2026年9月17日12:41

追加

                            run_elicitation
                        

2026年9月17日12:41

追加

                            update_operator_profile
                        

2026年9月17日12:41

追加

                            get_operator_profile
                        

2026年9月17日12:41

追加

                            check_deploy_readiness
                        

2026年9月17日12:41

追加

                            get_architecture_rationale
                        

2026年9月17日12:41

追加

                            get_incident_context
                        

2026年9月17日12:41

追加

                            get_escalation_recommendation
                        

2026年9月17日12:41

追加

                            declare_available_models
                        

2026年9月17日12:41

追加

                            fill_gap
                        

2026年9月17日12:41

追加

                            get_knowledge_gaps
                        

2026年9月17日12:41

追加

                            get_enrichment_status
                        

2026年9月17日12:41

追加

                            submit_correction
                        

2026年9月17日12:41

追加

                            investigate_question
                        

2026年9月17日12:41

追加

                            get_session_dossiers
                        

2026年9月17日12:41

追加

                            compare_versions
                        

2026年9月17日12:41

追加

                            extract_facts_from_sessions
                        

2026年9月17日12:41

追加

                            derive_from_facts
                        

2026年9月17日12:41

追加

                            assess_answerability
                        

2026年9月17日12:41

追加

                            expand_hit_context
                        

2026年9月17日12:41

追加

                            build_timeline
                        

2026年9月17日12:41

追加

                            enumerate_memory_facts
                        

2026年9月17日12:41

追加

                            list_external_services
                        

2026年9月17日12:41

追加

                            request_credentialed_call
                        

2026年9月17日12:41

追加

                            register_external_service
                        

2026年9月17日12:41

追加

                            log_progress
                        

2026年9月17日12:41

サーバー情報

バージョン

0.2.0

通信方式

Streamable HTTP

ツール

レイテンシ

3416 ms

最終スキャン

2026年10月1日2:45

初回確認

2026年9月13日2:14

エンドポイント

https://api.vaultcrux.com/memory-core/mcp

VaultCrux Memory Core

このMCPでできること

ツール

最近のツール変更

類似のMCPサーバー

AgentBoard

agent4.io

Swarmspace

mitosis

Remnant — Collective Memory & Evidence-Backed Trust for AI Agents

chp

agtrepo-memory

guide-registry