{"id":291154,"recorded_at":"2026-10-26T20:51:42.054710Z","observed_at":"2026-10-26T20:51:42.054563Z","subject_kind":"endpoint","subject":"786156be-07f0-4e45-bf9f-76fa35433251","kind":"mcp.tools","method":"probe.mcp/1","body":{"count":10,"tools":[{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"action":{"description":"The structured ProposedAction to evaluate.","properties":{"acting_agent_id":{"description":"Free-form id of the agent issuing the action.","type":"string"},"acting_agent_type":{"description":"Liability-bias category of the acting agent.","enum":["ai_system","vendor","deployer","operator","human_user","third_party"],"type":"string"},"action_id":{"description":"Stable id for this action; echoed back.","type":"string"},"action_type":{"description":"The action category. Carries inherent regulatory weight.","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"],"type":"string"},"cascade_depth":{"description":"How many upstream agents this action is downstream of. 0 = root; 3 = LLM->agent->tool->this. Applies cascade attenuation.","maximum":9007199254740991,"minimum":0,"type":"integer"},"context_flags":{"description":"Context flags that inform the regulatoryAlignment and controllability sub-scores.","properties":{"affects_vulnerable_population":{"type":"boolean"},"human_in_the_loop_present":{"type":"boolean"},"irreversible_if_executed":{"type":"boolean"},"regulated_domain":{"type":"boolean"}},"type":"object"},"eu_flags":{"description":"Optional EU AI Act flags; only used when jurisdiction === 'EU'.","properties":{"high_risk_ai":{"type":"boolean"},"human_oversight_unassigned_or_unqualified":{"type":"boolean"},"pld_compensable_damage":{"type":"boolean"}},"type":"object"},"jurisdiction":{"description":"Jurisdiction overlay; defaults to AU.","enum":["AU","EU","US","UK","CA"],"type":"string"},"severity_estimate":{"description":"The estimated severity if the action goes wrong.","enum":["low","medium","high","critical"],"type":"string"},"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"],"type":"object"},"overrides":{"description":"Optional per-call threshold override. Rationale REQUIRED for audit.","properties":{"allow_below":{"maximum":1,"minimum":0,"type":"number"},"block_at_or_above":{"maximum":1,"minimum":0,"type":"number"},"rationale":{"description":"REQUIRED when overrides are provided. Cite the governance basis (e.g. 'ISO/IEC 42001 SoA §3.2 approval').","type":"string"}},"required":["rationale"],"type":"object"}},"required":["action"],"type":"object"},"name":"evaluate_prospective_response"},{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"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"},"text":{"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.","maxLength":50000,"minLength":20,"type":"string"}},"required":["text"],"type":"object"},"name":"extract_incident"},{"description":"Return the index of all CausalLayer Tessera anchor batches, or one batch's full JSON (signed Merkle root, leaves, OpenTimestamps proof reference). FREE.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"version":{"description":"Optional anchor version, e.g. '2026-05-16-v1.6.4-simulation-calibration'.","type":"string"}},"type":"object"},"name":"get_anchor_status"},{"description":"Return the CausalLayer issuer registry, or one issuer record. The registry lists all trusted public-key fingerprints, key algorithms, validity windows, and the anchor-log repo for each active issuer. FREE — no API key required.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"issuer_id":{"description":"Optional issuer id, e.g. 'causallayer-prod-2026-q2'. If omitted, returns the full registry.","type":"string"}},"type":"object"},"name":"query_issuer_registry"},{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"actors":{"description":"All actors with the union of jurisdiction-specific role tags. EU and AU tags coexist on the same actor record.","items":{"properties":{"acl_supplier":{"type":"boolean"},"apra_regulated":{"type":"boolean"},"eu_chain_member":{"items":{"enum":["manufacturer","authorised_representative","importer","fulfilment_service_provider","distributor","online_platform_self_supplier","substantial_modifier"],"type":"string"},"type":"array"},"eu_resident":{"type":"boolean"},"id":{"type":"string"},"type":{"enum":["ai_system","vendor","deployer","human_operator","user","third_party"],"type":"string"},"unrecoverable":{"type":"boolean"}},"required":["id","type"],"type":"object"},"type":"array"},"attributable":{"additionalProperties":{"maximum":1,"minimum":0,"type":"number"},"description":"Canonical pre-overlay apportionment as { party_id: share }. Sum should approximate 1.0; the function renormalises within tolerance.","propertyNames":{"type":"string"},"type":"object"},"flags":{"description":"Union of jurisdiction-specific flags. AI Act / PLD flags drive the EU overlay; ACL / CPS 230 / VAISS flags drive the AU overlay.","properties":{"acl_major_failure":{"type":"boolean"},"ai_is_opaque_black_box":{"type":"boolean"},"cps230_operational_breach":{"type":"boolean"},"cps230_thirdparty_breach":{"type":"boolean"},"defendant_failed_disclosure_order":{"type":"boolean"},"deployer_destroyed_logs":{"type":"boolean"},"deployer_employer_no_worker_notice":{"type":"boolean"},"deployer_failed_serious_incident_notification":{"type":"boolean"},"deployer_ignored_risk_signal":{"type":"boolean"},"deployer_input_data_unrepresentative":{"type":"boolean"},"deployer_public_authority_unregistered":{"type":"boolean"},"deployer_used_contrary_to_instructions":{"type":"boolean"},"high_risk_ai":{"type":"boolean"},"human_oversight_nominally_assigned_not_present":{"type":"boolean"},"human_oversight_unassigned_or_unqualified":{"type":"boolean"},"is_apra_regulated_service":{"type":"boolean"},"pld_compensable_damage":{"type":"boolean"},"provider_breach_was_unforeseeable":{"type":"boolean"},"provider_failed_to_supply_instructions":{"type":"boolean"},"substantial_modification_present":{"type":"boolean"},"substantial_modification_severity":{"maximum":1,"minimum":0,"type":"number"},"vaiss_adherent":{"type":"boolean"},"vendor_no_docs":{"type":"boolean"}},"type":"object"},"jurisdictions":{"description":"Optional subset to compute. Defaults to all five.","items":{"enum":["AU","EU","US","UK","CA"],"type":"string"},"type":"array"},"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"],"type":"object"},"name":"query_jurisdiction_overlay"},{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"agents":{"description":"Agent registry (id + type) so the simulator can map remediation targetType to specific party ids.","items":{"properties":{"id":{"type":"string"},"type":{"type":"string"}},"required":["id"],"type":"object"},"type":"array"},"fourFactorScoring":{"description":"The fourFactorScoring block from the CausalCertificate.","properties":{"behaviouralDeviation":{"maximum":1,"minimum":0,"type":"number"},"causalProximity":{"maximum":1,"minimum":0,"type":"number"},"controllability":{"maximum":1,"minimum":0,"type":"number"},"primaryAgent":{"type":"string"},"regulatoryAlignment":{"maximum":1,"minimum":0,"type":"number"},"weights":{"properties":{"behaviouralDeviation":{"type":"number"},"causalProximity":{"type":"number"},"controllability":{"type":"number"},"regulatoryAlignment":{"type":"number"}},"required":["causalProximity","behaviouralDeviation","controllability","regulatoryAlignment"],"type":"object"}},"required":["primaryAgent","causalProximity","behaviouralDeviation","controllability","regulatoryAlignment","weights"],"type":"object"},"remediations":{"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.","items":{"properties":{"appliedToParty":{"type":"string"},"id":{"type":"string"}},"required":["id"],"type":"object"},"minItems":1,"type":"array"},"verdict":{"description":"The verdict block from the CausalCertificate.","properties":{"primaryParty":{"type":"string"},"primaryShare":{"maximum":1,"minimum":0,"type":"number"},"secondary":{"items":{"properties":{"party":{"type":"string"},"share":{"maximum":1,"minimum":0,"type":"number"}},"required":["party","share"],"type":"object"},"type":"array"}},"required":["primaryParty","primaryShare","secondary"],"type":"object"}},"required":["verdict","fourFactorScoring","agents","remediations"],"type":"object"},"name":"simulate_remediation"},{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"agents":{"items":{"properties":{"id":{"minLength":1,"type":"string"},"model_id":{"type":"string"},"name":{"minLength":1,"type":"string"},"operator_role":{"enum":["provider","deployer","user","vendor","regulator","auditor"],"type":"string"},"type":{"enum":["ai_system","human_operator","vendor","deployer","user","third_party"],"type":"string"},"vendor_name":{"type":"string"}},"required":["id","name","type"],"type":"object"},"minItems":1,"type":"array"},"category":{"type":"string"},"currency":{"maxLength":3,"minLength":3,"type":"string"},"description":{"type":"string"},"deterministic_only":{"const":true,"description":"G2: Must be true. Acknowledges CausalLayer is deterministic and not LLM-based.","type":"boolean"},"events":{"items":{"properties":{"actor_id":{"type":"string"},"description":{"minLength":1,"type":"string"},"id":{"minLength":1,"type":"string"},"span_id":{"pattern":"^[0-9a-f]{16}$","type":"string"},"timestamp":{"minLength":1,"type":"string"},"trace_id":{"pattern":"^[0-9a-f]{32}$","type":"string"},"trace_source":{"enum":["opentelemetry","jaeger","zipkin","datadog","newrelic","other"],"type":"string"},"type":{"minLength":1,"type":"string"}},"required":["id","type","timestamp","description"],"type":"object"},"minItems":1,"type":"array"},"financial_impact_cents":{"anyOf":[{"maximum":9007199254740991,"minimum":0,"type":"integer"},{"type":"null"}]},"jurisdiction":{"type":"string"},"pii_acknowledged":{"default":false,"description":"G1: Set to true ONLY if caller has confirmed PII handling is permitted by their data agreement. False payloads with detected PII will be rejected.","type":"boolean"},"severity":{"enum":["low","medium","high","critical"],"type":"string"},"title":{"minLength":3,"type":"string"}},"required":["title","agents","events","deterministic_only"],"type":"object"},"name":"submit_incident"},{"description":"Convert an OpenTelemetry OTLP JSON trace into a FaultKey incident and return the same deterministic CausalCertificate as submit_incident. Each span becomes an event; service.name groups spans into agents; W3C trace_id and span_id propagate as evidence pointers on the causal graph edges. Cost: 50 credits (same as submit_incident). Three guardrails apply: PII scan, deterministic-only acknowledgement, and minimum evidence (auto-satisfied when the trace has at least 1 span).","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"category":{"type":"string"},"currency":{"maxLength":3,"minLength":3,"type":"string"},"deterministic_only":{"const":true,"description":"G2: Must be true. Acknowledges CausalLayer is deterministic.","type":"boolean"},"financial_impact_cents":{"anyOf":[{"maximum":9007199254740991,"minimum":0,"type":"integer"},{"type":"null"}]},"jurisdiction":{"type":"string"},"otlp":{"additionalProperties":{},"description":"OTLP JSON payload with resourceSpans[]. See https://opentelemetry.io/docs/specs/otlp/#json-protobuf-encoding","propertyNames":{"type":"string"},"type":"object"},"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"},"title":{"minLength":3,"type":"string"}},"required":["title","otlp","deterministic_only"],"type":"object"},"name":"submit_otel_trace"},{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"certificate":{"additionalProperties":{},"description":"CausalCertificateV1 object as returned by submit_incident.certificate","propertyNames":{"type":"string"},"type":"object"}},"required":["certificate"],"type":"object"},"name":"verify_certificate"},{"description":"Independently re-derive a CausalCertificate from its canonical input and compare byte-for-byte against the claimed certificate. This is the strongest verification path: it requires no trust in the issuer or signing key. Cost: 1 credit (same price as verify_certificate). Returns PASS only if every checked field (certificateId, request_hash, merkleRoot, verdict, causalGraph, fourFactorScoring, deviationTaxonomy, euRuleOverlay, cascadeAttenuation, damages, underwriting) matches identically.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"canonicalInput":{"additionalProperties":{},"description":"The original incident body that produced the certificate — the same JSON originally posted to submit_incident or submit_otel_trace.","propertyNames":{"type":"string"},"type":"object"},"certificate":{"additionalProperties":{},"description":"The CausalCertificate object claimed by the issuer.","propertyNames":{"type":"string"},"type":"object"}},"required":["certificate","canonicalInput"],"type":"object"},"name":"verify_certificate_recompute"}]},"body_sha256":"79b6ec8575710695ce8b07f319a25fe8aa2aeae9ca82c8f4855dbc8becf0d0b4","prev_id":null,"leaf":"0x47bff0025fd1882a97d54182583c8fa81faf57fdcad8902bfef9caaba2c3b4a9","leaf_text":"{\"body\":\"79b6ec8575710695ce8b07f319a25fe8aa2aeae9ca82c8f4855dbc8becf0d0b4\",\"id\":291154,\"kind\":\"mcp.tools\",\"method\":\"probe.mcp/1\",\"observed_us\":1793047902054563,\"prev\":null,\"subject\":\"786156be-07f0-4e45-bf9f-76fa35433251\",\"subject_kind\":\"endpoint\"}","day":{"day":"2026-10-26","leaves":296695,"root":"0xf43e8dcc3d451a4788b26be904c55e8c4c0fa75c9666796c51db38d37e2c0df8","chained":"0x702d5ac508f08b0d1accf36af25822d8e5660367494edd17a642fb61e158a57a","anchor_chain":"eip155:5042002","anchor_tx":"0x495162f8936e19f0039918feebe6c307f327cd6bf8c37219620b1970041fa9ae","anchor_block":69251483},"proof":["0x47c0419a9211090fbdfd8494159fe1ab7c7c3df2921d433a4a99703e4db8d63a","0x2cedbd844dc44c0f9b6bbc9dd234c12f654ec8662029835ed14869a557fdf1e8","0x50e35855819f3ef6dcf5e6d8348221f33de94fb46c87c1d26a9a47cba38d690b","0x040f85646192e31ff327a47c3a83c52c30b51f5a6510016f6728ed66f5b49d5b","0xa429f41c9cf62fcedf7f0774a1f4cb2383dd5431b2a12cfad2340cc025fa10ba","0xa16f0917b884e4ecb367b9312ad451c474a0e4bd37c74d7c2c65f28db5a078df","0x6bbdd3a72b2cea2d5c982707264ec7cf4785b7842667e3189d4ce6ad0b6279b2","0x6754f8d808e824d9b00a10cf3ab2375ccc5ede502b1993e7cc096a80d4e23b65","0xf02d809f1bfb0c9c066592febb7be763756e0e3c85b36321e582d37336797b8c","0x67d81f51788e4acdc8f36ca9346a133b005814670585625cf73534b4509e188a","0x263cc8bcddc70acc00ef06b84397a006a822410dc2b18b714a0be72a820c5b17","0xae3550e71ca4b0f0b86c9905b234388d6bc01a22e52324fb1ee62a553273a1fe","0xb86fa861d04737cb507e721eefbb066d26528fdb6017b1145c18d1223b93ee21","0x88e326a39b26e2c125306c9d3805d14398ace088bba9a2a0aa376b811cfb201a","0x2be1e80e065dd6b2cc75a7142be22225acd144ac975d70bf24b4f01fd76dc497","0x2e6a32eb32761c210560e852405e2f865f958ddbe01027894f8b9c1b3433b9f0","0x9a83be955a206deb65b995adfd92c58fa31c95fbbf926bd199d300e70b08b26d","0x20704208aa6923d6b2450ef74ede87a6e0265d46447926038fe9506e9e154b2d","0x9b9ce5b74b9bab5121612ef6b64920a8d453cbf311096a423eef9702747e868a"]}