FaultKey · CausalLayer
Deterministic AI-liability attribution: signed, Bitcoin-anchored vendor/deployer/user fault split.
사용해야 할까요
품질 및 안전성
도구 정의와 프로토콜 준수에 대한 자동 분석을 기반으로 합니다.
컨텍스트 비용
이는 서버의 도구가 모델의 컨텍스트에 로드될 때마다 소비되는 대략적인 토큰 수입니다. 수치가 높을수록 다른 작업에 사용할 수 있는 주의가 줄어듭니다.
설치
원클릭 설치
`claude_desktop_config.json` 파일에 다음을 추가하세요:
{
"mcpServers": {
"causallayer-mcp": {
"url": "https://causallayer-mcp-demo.zykm9qkk7j.workers.dev/mcp"
}
}
}원격 엔드포인트
https://causallayer-mcp-demo.zykm9qkk7j.workers.dev/mcpstreamable-http할 수 있는 일
도구 목록
도구 (10)
🟡submit_incident(title, description, category, severity, jurisdiction, ...)
Submit an AI incident for deterministic causal liability attribution. Returns a signed CausalCertificate, per-agent liability allocation, evidence-chain completeness, regulatory mapping, and (where keys are configured) a Bitcoin-anchored proof. Cost: 50 credits. Three guardrails apply: PII scan, deterministic-only acknowledgement, and minimum evidence.
입력 스키마
{
"type": "object",
"properties": {
"title": {
"type": "string",
"minLength": 3
},
"description": {
"type": "string"
},
"category": {
"type": "string"
},
"severity": {
"type": "string",
"enum": [
"low",
"medium",
"high",
"critical"
]
},
"jurisdiction": {
"type": "string"
},
"financial_impact_cents": {
"anyOf": [
{
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"currency": {
"type": "string",
"minLength": 3,
"maxLength": 3
},
"agents": {
"minItems": 1,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1
},
"name": {
"type": "string",
"minLength": 1
},
"type": {
"type": "string",
"enum": [
"ai_system",
"human_operator",
"vendor",
"deployer",
"user",
"third_party"
]
},
"operator_role": {
"type": "string",
"enum": [
"provider",
"deployer",
"user",
"vendor",
"regulator",
"auditor"
]
},
"vendor_name": {
"type": "string"
},
"model_id": {
"type": "string"
}
},
"required": [
"id",
"name",
"type"
]
}
},
"events": {
"minItems": 1,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"minLength": 1
},
"type": {
"type": "string",
"minLength": 1
},
"timestamp": {
"type": "string",
"minLength": 1
},
"actor_id": {
"type": "string"
},
"description": {
"type": "string",
"minLength": 1
},
"trace_id": {
"type": "string",
"pattern": "^[0-9a-f]{32}$"
},
"span_id": {
"type": "string",
"pattern": "^[0-9a-f]{16}$"
},
"trace_source": {
"type": "string",
"enum": [
"opentelemetry",
"jaeger",
"zipkin",
"datadog",
"newrelic",
"other"
]
}
},
"required": [
"id",
"type",
"timestamp",
"description"
]
}
},
"deterministic_only": {
"type": "boolean",
"const": true,
"description": "G2: Must be true. Acknowledges CausalLayer is deterministic and not LLM-based."
},
"pii_acknowledged": {
"default": false,
"description": "G1: Set to true ONLY if caller has confirmed PII handling is permitted by their data agreement. False payloads with detected PII will be rejected.",
"type": "boolean"
}
},
"required": [
"title",
"agents",
"events",
"deterministic_only"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪verify_certificate(certificate)
Independently verify a CausalCertificate end-to-end (signature, Merkle integrity, issuer status against the registry). Cost: 1 credit. In production env, certificates from non-active issuers are rejected.
입력 스키마
{
"type": "object",
"properties": {
"certificate": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "CausalCertificateV1 object as returned by submit_incident.certificate"
}
},
"required": [
"certificate"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪verify_certificate_recompute(certificate, canonicalInput)
Independently re-derive a CausalCertificate from its canonical input and compare byte-for-byte against the claimed certificate. This is the strongest verification path: it requires no trust in the issuer or signing key. Cost: 1 credit (same price as verify_certificate). Returns PASS only if every checked field (certificateId, request_hash, merkleRoot, verdict, causalGraph, fourFactorScoring, deviationTaxonomy, euRuleOverlay, cascadeAttenuation, damages, underwriting) matches identically.
입력 스키마
{
"type": "object",
"properties": {
"certificate": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "The CausalCertificate object claimed by the issuer."
},
"canonicalInput": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "The original incident body that produced the certificate — the same JSON originally posted to submit_incident or submit_otel_trace."
}
},
"required": [
"certificate",
"canonicalInput"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡submit_otel_trace(title, otlp, category, jurisdiction, financial_impact_cents, ...)
Convert an OpenTelemetry OTLP JSON trace into a FaultKey incident and return the same deterministic CausalCertificate as submit_incident. Each span becomes an event; service.name groups spans into agents; W3C trace_id and span_id propagate as evidence pointers on the causal graph edges. Cost: 50 credits (same as submit_incident). Three guardrails apply: PII scan, deterministic-only acknowledgement, and minimum evidence (auto-satisfied when the trace has at least 1 span).
입력 스키마
{
"type": "object",
"properties": {
"title": {
"type": "string",
"minLength": 3
},
"otlp": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {},
"description": "OTLP JSON payload with resourceSpans[]. See https://opentelemetry.io/docs/specs/otlp/#json-protobuf-encoding"
},
"category": {
"type": "string"
},
"jurisdiction": {
"type": "string"
},
"financial_impact_cents": {
"anyOf": [
{
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
{
"type": "null"
}
]
},
"currency": {
"type": "string",
"minLength": 3,
"maxLength": 3
},
"deterministic_only": {
"type": "boolean",
"const": true,
"description": "G2: Must be true. Acknowledges CausalLayer is deterministic."
},
"pii_acknowledged": {
"default": false,
"description": "G1: Set to true ONLY if PII handling is permitted by your data agreement. OTLP traces frequently leak user/session ids in attributes.",
"type": "boolean"
}
},
"required": [
"title",
"otlp",
"deterministic_only"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢simulate_remediation(verdict, fourFactorScoring, agents, remediations)
Counterfactual remediation simulator. Given a certificate's verdict + fourFactorScoring + agents and a list of remediation IDs from the FK-METHOD-2026-003 catalog, return the apportioned shares each remediation would have produced (in isolation) and the composite shares if they all stack. Every remediation cites a specific statute or standard. GET /api/v2/remediation/catalog for the list of IDs. Cost: 1 credit (same price as verify_certificate). Pure deterministic; same inputs produce a byte-identical result.
입력 스키마
{
"type": "object",
"properties": {
"verdict": {
"type": "object",
"properties": {
"primaryParty": {
"type": "string"
},
"primaryShare": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"secondary": {
"type": "array",
"items": {
"type": "object",
"properties": {
"party": {
"type": "string"
},
"share": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"party",
"share"
]
}
}
},
"required": [
"primaryParty",
"primaryShare",
"secondary"
],
"description": "The verdict block from the CausalCertificate."
},
"fourFactorScoring": {
"type": "object",
"properties": {
"primaryAgent": {
"type": "string"
},
"causalProximity": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"behaviouralDeviation": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"controllability": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"regulatoryAlignment": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"weights": {
"type": "object",
"properties": {
"causalProximity": {
"type": "number"
},
"behaviouralDeviation": {
"type": "number"
},
"controllability": {
"type": "number"
},
"regulatoryAlignment": {
"type": "number"
}
},
"required": [
"causalProximity",
"behaviouralDeviation",
"controllability",
"regulatoryAlignment"
]
}
},
"required": [
"primaryAgent",
"causalProximity",
"behaviouralDeviation",
"controllability",
"regulatoryAlignment",
"weights"
],
"description": "The fourFactorScoring block from the CausalCertificate."
},
"agents": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string"
}
},
"required": [
"id"
]
},
"description": "Agent registry (id + type) so the simulator can map remediation targetType to specific party ids."
},
"remediations": {
"minItems": 1,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"appliedToParty": {
"type": "string"
}
},
"required": [
"id"
]
},
"description": "List of remediation IDs from the catalog (e.g. vendor_adversarial_eval_suite, deployer_human_in_loop). Each may optionally pin appliedToParty to a specific agent id."
}
},
"required": [
"verdict",
"fourFactorScoring",
"agents",
"remediations"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡query_jurisdiction_overlay(attributable, actors, flags, jurisdictions, primaryJurisdiction)
Multi-jurisdiction overlay (FK-METHOD-2026-004). Given a canonical attributable apportionment (party-id -> share), the union of all jurisdiction role tags on each actor, and the union of jurisdiction-specific flags, return side-by-side post-overlay shares for AU, EU, US, UK, CA (or a chosen subset) with the specific rules that fired in each, citation URLs, and a parties × jurisdictions matrix. v1 ships full implementations for AU and EU; US/UK/CA are research stubs marked `is_stub: true`. Use GET /api/v2/jurisdiction/catalog to discover support and stub status. Cost: 1 credit. Pure deterministic.
입력 스키마
{
"type": "object",
"properties": {
"attributable": {
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"description": "Canonical pre-overlay apportionment as { party_id: share }. Sum should approximate 1.0; the function renormalises within tolerance."
},
"actors": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"type": {
"type": "string",
"enum": [
"ai_system",
"vendor",
"deployer",
"human_operator",
"user",
"third_party"
]
},
"eu_chain_member": {
"type": "array",
"items": {
"type": "string",
"enum": [
"manufacturer",
"authorised_representative",
"importer",
"fulfilment_service_provider",
"distributor",
"online_platform_self_supplier",
"substantial_modifier"
]
}
},
"eu_resident": {
"type": "boolean"
},
"apra_regulated": {
"type": "boolean"
},
"acl_supplier": {
"type": "boolean"
},
"unrecoverable": {
"type": "boolean"
}
},
"required": [
"id",
"type"
]
},
"description": "All actors with the union of jurisdiction-specific role tags. EU and AU tags coexist on the same actor record."
},
"flags": {
"type": "object",
"properties": {
"high_risk_ai": {
"type": "boolean"
},
"pld_compensable_damage": {
"type": "boolean"
},
"deployer_used_contrary_to_instructions": {
"type": "boolean"
},
"human_oversight_unassigned_or_unqualified": {
"type": "boolean"
},
"human_oversight_nominally_assigned_not_present": {
"type": "boolean"
},
"deployer_input_data_unrepresentative": {
"type": "boolean"
},
"deployer_ignored_risk_signal": {
"type": "boolean"
},
"deployer_failed_serious_incident_notification": {
"type": "boolean"
},
"deployer_destroyed_logs": {
"type": "boolean"
},
"deployer_employer_no_worker_notice": {
"type": "boolean"
},
"deployer_public_authority_unregistered": {
"type": "boolean"
},
"provider_failed_to_supply_instructions": {
"type": "boolean"
},
"provider_breach_was_unforeseeable": {
"type": "boolean"
},
"ai_is_opaque_black_box": {
"type": "boolean"
},
"defendant_failed_disclosure_order": {
"type": "boolean"
},
"substantial_modification_present": {
"type": "boolean"
},
"substantial_modification_severity": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"acl_major_failure": {
"type": "boolean"
},
"is_apra_regulated_service": {
"type": "boolean"
},
"cps230_thirdparty_breach": {
"type": "boolean"
},
"cps230_operational_breach": {
"type": "boolean"
},
"vaiss_adherent": {
"type": "boolean"
},
"vendor_no_docs": {
"type": "boolean"
}
},
"description": "Union of jurisdiction-specific flags. AI Act / PLD flags drive the EU overlay; ACL / CPS 230 / VAISS flags drive the AU overlay."
},
"jurisdictions": {
"description": "Optional subset to compute. Defaults to all five.",
"type": "array",
"items": {
"type": "string",
"enum": [
"AU",
"EU",
"US",
"UK",
"CA"
]
}
},
"primaryJurisdiction": {
"description": "Engine-level jurisdiction string (e.g. 'EU', 'DE', 'AU'). Used by the EU gate to decide engagement.",
"type": "string"
}
},
"required": [
"attributable",
"actors",
"flags"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡evaluate_prospective_response(action, overrides)
Deterministic prospective-evaluation gate (FK-METHOD-2026-006). Pass a ProposedAction BEFORE the agent delivers a response; receive one of three verdicts: 'allow', 'require_revision' (with specific factor-keyed directives), or 'block'. Uses the same four-factor engine that issues post-hoc certificates, so a single incident chains: prospective_pre_image -> response -> certificate -> anchor. This is a policy gate on structured action metadata, NOT a content safety classifier on raw prose. Thresholds are per-jurisdiction (EU strictest, US most permissive); read via GET /api/v2/gate/thresholds. Overrides are allowed but REQUIRE a governance rationale so the audit trail is complete. Cost: 1 credit. Pure deterministic.
입력 스키마
{
"type": "object",
"properties": {
"action": {
"type": "object",
"properties": {
"action_id": {
"type": "string",
"description": "Stable id for this action; echoed back."
},
"action_type": {
"type": "string",
"enum": [
"llm_response",
"tool_call",
"code_execution",
"external_api_call",
"human_handoff",
"data_modification",
"financial_transaction",
"medical_advice",
"legal_advice",
"financial_advice",
"content_moderation",
"autonomous_decision",
"other"
],
"description": "The action category. Carries inherent regulatory weight."
},
"acting_agent_id": {
"type": "string",
"description": "Free-form id of the agent issuing the action."
},
"acting_agent_type": {
"type": "string",
"enum": [
"ai_system",
"vendor",
"deployer",
"operator",
"human_user",
"third_party"
],
"description": "Liability-bias category of the acting agent."
},
"severity_estimate": {
"type": "string",
"enum": [
"low",
"medium",
"high",
"critical"
],
"description": "The estimated severity if the action goes wrong."
},
"jurisdiction": {
"description": "Jurisdiction overlay; defaults to AU.",
"type": "string",
"enum": [
"AU",
"EU",
"US",
"UK",
"CA"
]
},
"cascade_depth": {
"description": "How many upstream agents this action is downstream of. 0 = root; 3 = LLM->agent->tool->this. Applies cascade attenuation.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"eu_flags": {
"description": "Optional EU AI Act flags; only used when jurisdiction === 'EU'.",
"type": "object",
"properties": {
"high_risk_ai": {
"type": "boolean"
},
"pld_compensable_damage": {
"type": "boolean"
},
"human_oversight_unassigned_or_unqualified": {
"type": "boolean"
}
}
},
"context_flags": {
"description": "Context flags that inform the regulatoryAlignment and controllability sub-scores.",
"type": "object",
"properties": {
"affects_vulnerable_population": {
"type": "boolean"
},
"regulated_domain": {
"type": "boolean"
},
"irreversible_if_executed": {
"type": "boolean"
},
"human_in_the_loop_present": {
"type": "boolean"
}
}
},
"upstream_incident_id": {
"description": "Optional chain to an existing incident trace.",
"type": "string"
}
},
"required": [
"action_id",
"action_type",
"acting_agent_id",
"acting_agent_type",
"severity_estimate"
],
"description": "The structured ProposedAction to evaluate."
},
"overrides": {
"description": "Optional per-call threshold override. Rationale REQUIRED for audit.",
"type": "object",
"properties": {
"allow_below": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"block_at_or_above": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"rationale": {
"type": "string",
"description": "REQUIRED when overrides are provided. Cite the governance basis (e.g. 'ISO/IEC 42001 SoA §3.2 approval')."
}
},
"required": [
"rationale"
]
}
},
"required": [
"action"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_anchor_status(version)
Return the index of all CausalLayer Tessera anchor batches, or one batch's full JSON (signed Merkle root, leaves, OpenTimestamps proof reference). FREE.
입력 스키마
{
"type": "object",
"properties": {
"version": {
"description": "Optional anchor version, e.g. '2026-05-16-v1.6.4-simulation-calibration'.",
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢query_issuer_registry(issuer_id)
Return the CausalLayer issuer registry, or one issuer record. The registry lists all trusted public-key fingerprints, key algorithms, validity windows, and the anchor-log repo for each active issuer. FREE — no API key required.
입력 스키마
{
"type": "object",
"properties": {
"issuer_id": {
"description": "Optional issuer id, e.g. 'causallayer-prod-2026-q2'. If omitted, returns the full registry.",
"type": "string"
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡extract_incident(text, context_hint, jurisdiction_hint)
Claude-powered structured extractor. Parses unstructured text (news articles, court filings, emails, PDFs, incident reports, logs) into the typed JSON schema required by submit_incident. Returns a ready-to-submit incident object with extracted agents, events, severity, jurisdiction, and financial impact. NOTE: This is a pre-processing convenience tool — the deterministic scoring engine itself remains LLM-free. Cost: 10 credits.
입력 스키마
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 20,
"maxLength": 50000,
"description": "Unstructured text to extract from. Can be a news article, court filing, incident report, email, PDF text, log output, or any description of an AI incident."
},
"context_hint": {
"description": "Optional hint about the source type (e.g., 'court filing', 'news article', 'internal incident report') to improve extraction accuracy.",
"type": "string"
},
"jurisdiction_hint": {
"description": "Optional ISO country code hint if the jurisdiction is known (e.g., 'AU', 'US', 'EU').",
"type": "string"
}
},
"required": [
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}커뮤니티
증거