io.github.smq9sn5jck-cloud/causallayer-mcp

Est-ce que io.github.smq9sn5jck-cloud/causallayer-mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.smq9sn5jck-cloud/causallayer-mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

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

Les 10 outils

• evaluate_prospective_response≈ 890 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • action · object · requis
    The structured ProposedAction to evaluate.
  • overrides · object · optionnel
    Optional per-call threshold override. Rationale REQUIRED for audit.

  Exemple d'appel

  {"name": "evaluate_prospective_response", "arguments": {"action": {}}}

  Exemple de retour

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

• extract_incident≈ 294 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • text · string · requis
    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 · string · optionnel
    Optional hint about the source type (e.g., 'court filing', 'news article', 'internal incident report') to improve extraction accuracy.
  • jurisdiction_hint · string · optionnel
    Optional ISO country code hint if the jurisdiction is known (e.g., 'AU', 'US', 'EU').

  Exemple d'appel

  {"name": "extract_incident", "arguments": {"text": "texte"}}

  Exemple de retour

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

• get_anchor_status≈ 107 tokens

  Return the index of all CausalLayer Tessera anchor batches, or one batch's full JSON (signed Merkle root, leaves, OpenTimestamps proof reference). FREE.

  Paramètres, retour & exemple (1)

  Paramètres

  • version · string · optionnel
    Optional anchor version, e.g. '2026-05-16-v1.6.4-simulation-calibration'.

  Exemple d'appel

  {"name": "get_anchor_status", "arguments": {"version": "texte"}}

  Exemple de retour

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

• query_issuer_registry≈ 132 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • issuer_id · string · optionnel
    Optional issuer id, e.g. 'causallayer-prod-2026-q2'. If omitted, returns the full registry.

  Exemple d'appel

  {"name": "query_issuer_registry", "arguments": {"issuer_id": "texte"}}

  Exemple de retour

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

• query_jurisdiction_overlay≈ 917 tokens

  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.

  Paramètres, retour & exemple (5)

  Paramètres

  • flags · object · requis
    Union of jurisdiction-specific flags. AI Act / PLD flags drive the EU overlay; ACL / CPS 230 / VAISS flags drive the AU overlay.
  • actors · array · requis
    All actors with the union of jurisdiction-specific role tags. EU and AU tags coexist on the same actor record.
  • attributable · object · requis
    Canonical pre-overlay apportionment as { party_id: share }. Sum should approximate 1.0; the function renormalises within tolerance.
  • jurisdictions · array · optionnel
    Optional subset to compute. Defaults to all five.
  • primaryJurisdiction · string · optionnel
    Engine-level jurisdiction string (e.g. 'EU', 'DE', 'AU'). Used by the EU gate to decide engagement.

  Exemple d'appel

  {"name": "query_jurisdiction_overlay", "arguments": {"flags": {}, "actors": [], "attributable": {}}}

  Exemple de retour

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

• simulate_remediation≈ 679 tokens

  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.

  Paramètres, retour & exemple (4)

  Paramètres

  • agents · array · requis
    Agent registry (id + type) so the simulator can map remediation targetType to specific party ids.
  • verdict · object · requis
    The verdict block from the CausalCertificate.
  • remediations · array · requis
    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.
  • fourFactorScoring · object · requis
    The fourFactorScoring block from the CausalCertificate.

  Exemple d'appel

  {"name": "simulate_remediation", "arguments": {"agents": [], "verdict": {}, "remediations": [], "fourFactorScoring": {}}}

  Exemple de retour

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

• submit_incident≈ 616 tokens

  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.

  Paramètres, retour & exemple (11)

  Paramètres

  • title · string · requis
  • agents · array · requis
  • events · array · requis
  • category · string · optionnel
  • currency · string · optionnel
  • severity · string · optionnel · low | medium | high | critical
  • description · string · optionnel
  • jurisdiction · string · optionnel
  • pii_acknowledged · boolean · optionnel
    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.
  • deterministic_only · boolean · requis
    G2: Must be true. Acknowledges CausalLayer is deterministic and not LLM-based.
  • financial_impact_cents · ? · optionnel

  Exemple d'appel

  {"name": "submit_incident", "arguments": {"title": "texte", "agents": [], "events": [], "deterministic_only": true}}

  Exemple de retour

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

• submit_otel_trace≈ 387 tokens

  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).

  Paramètres, retour & exemple (8)

  Paramètres

  • otlp · object · requis
    OTLP JSON payload with resourceSpans[]. See https://opentelemetry.io/docs/specs/otlp/#json-protobuf-encoding
  • title · string · requis
  • category · string · optionnel
  • currency · string · optionnel
  • jurisdiction · string · optionnel
  • pii_acknowledged · boolean · optionnel
    G1: Set to true ONLY if PII handling is permitted by your data agreement. OTLP traces frequently leak user/session ids in attributes.
  • deterministic_only · boolean · requis
    G2: Must be true. Acknowledges CausalLayer is deterministic.
  • financial_impact_cents · ? · optionnel

  Exemple d'appel

  {"name": "submit_otel_trace", "arguments": {"otlp": {}, "title": "texte", "deterministic_only": true}}

  Exemple de retour

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

• verify_certificate≈ 144 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • certificate · object · requis
    CausalCertificateV1 object as returned by submit_incident.certificate

  Exemple d'appel

  {"name": "verify_certificate", "arguments": {"certificate": {}}}

  Exemple de retour

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

• verify_certificate_recompute≈ 282 tokens

  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.

  Paramètres, retour & exemple (2)

  Paramètres

  • certificate · object · requis
    The CausalCertificate object claimed by the issuer.
  • canonicalInput · object · requis
    The original incident body that produced the certificate — the same JSON originally posted to submit_incident or submit_otel_trace.

  Exemple d'appel

  {"name": "verify_certificate_recompute", "arguments": {"certificate": {}, "canonicalInput": {}}}

  Exemple de retour

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

C'est votre serveur ?

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

Créer un compte / revendiquer →

Source

https://causallayer-mcp-demo.zykm9qkk7j.workers.dev/mcp