io.github.InterAILabs/ai-risk-oracle

Est-ce que io.github.InterAILabs/ai-risk-oracle est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.InterAILabs/ai-risk-oracle » 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 9 outils

• oracle.agent_card≈ 354 tokens

  Read-only A2A Agent Card with agent identity, security scheme, capabilities, and skills. Use it when selecting or integrating InterAI through A2A; use oracle.service_descriptor for general service metadata or oracle.discovery_bundle for complete bootstrap context.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "oracle.agent_card", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"url": "texte", "name": "texte", "skills": [], "version": "texte", "provider": {}, "security": [], "description": "texte", "capabilities": {}, "securitySchemes": {}, "documentationUrl": "texte", "defaultInputModes": [], "defaultOutputModes": []}}

• oracle.discovery_bundle≈ 306 tokens

  Read-only bootstrap or handoff bundle with service identity, interfaces, runtime mode, contracts, schemas, and sample payloads in one response. Use it for complete integration context; use oracle.service_descriptor for focused service metadata, oracle.agent_card for A2A capabilities, or oracle.get_pricing for costs.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "oracle.discovery_bundle", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "runtime": {}, "samples": {}, "service": {}, "discovery": {}, "interfaces": {}}}

• oracle.get_pricing≈ 355 tokens

  Read-only public metadata for costs, trial availability, idempotency, and top-up or payment paths. Use it before budgeting or onboarding; it does not evaluate risk or create a trust receipt.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "oracle.get_pricing", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"auth": {}, "demo": {}, "unit": "texte", "chain": "texte", "model": "texte", "topup": {}, "trial": {}, "verify": {}, "currency": "texte", "protocols": {}, "idempotency": {}, "verify_batch": {}}}

• oracle.get_trust_receipt≈ 518 tokens

  Read-only lookup of the canonical public representation and signature metadata for a trust receipt that already exists. Supply receipt_id. It does not create or re-run a decision; use oracle.verify_trust_receipt_signature when the goal is signature validation.

  Paramètres, retour & exemple (1)

  Paramètres

  • receipt_id · string · requis
    Identifier of the existing InterAI trust receipt whose canonical public representation and signature metadata should be returned.

  Exemple d'appel

  {"name": "oracle.get_trust_receipt", "arguments": {"receipt_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"ok": true, "trust": {}, "receipt": {}, "verification": {}}}

• oracle.service_descriptor≈ 318 tokens

  Read-only general service descriptor with identity, endpoints, billing, trust, and supported agent protocols. Use it to inspect service-level integration metadata; use oracle.agent_card for A2A skills or oracle.discovery_bundle for the complete bootstrap package.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "oracle.service_descriptor", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"id": "texte", "name": "texte", "billing": {}, "version": "texte", "discovery": {}, "endpoints": {}, "description": "texte", "agent_protocols": {}}}

• oracle.verify_autonomous_action≈ 6002 tokens

  Primary tool for one concrete proposed autonomous action before it executes. This authenticated prepaid verification may consume account balance and records a signed trust receipt; InterAI evaluates the proposal but does not execute or modify the proposed external action. Reuse idempotency_key only when retrying the same logical request to avoid duplicate billing. Returns allow, review_required, or block with policy signals. Use oracle.verify_batch for multiple independent items and oracle.verify_response only for legacy prompt/response compatibility.

  Paramètres, retour & exemple (10)

  Paramètres

  • mode · string · optionnel · fast_heuristic | semantic_judge
    Verification mode. Use fast_heuristic for the default low-latency path or semantic_judge when a semantic model judgment is explicitly required.
  • action · object · requis
    The proposed action. For executable pilot authorization use interai-canonical-action/v1 with host-registry tool_id, type, operation, exact arguments, and explicit side-effect semantics.
  • domain · string · optionnel
    Optional domain label used to provide verification context. It does not replace the exact action, context, or policy inputs.
  • policy · object · optionnel
    Optional strictly validated caller-scoped restrictions. They may tighten the boundary but cannot weaken host or account policy.
  • context · object · optionnel
    Optional runtime context surrounding the proposed action, such as environment, agent identity, counterparty, user confirmation, or other facts relevant to this decision.
  • use_case · string · requis
    Stable identifier describing why the exact autonomous action is being proposed. Required together with action for the autonomous_execution contract.
  • idempotency_key · string · optionnel
    Stable caller-provided key for retrying the same billed verification without duplicating the economic operation. Reuse it only for the same logical request.
  • execution_context · object · optionnel
    Host-attested execution context bound to a canonical action. InterAI authenticates the account, not the truth of host-provided workspace, actor, run, or environment values.
  • external_evidence · array · optionnel
    Optional signed or verifiable external assertions. Current Stage 2 evidence is parsed, verified, bound, and recorded as non-authoritative evidence; it does not directly determine the InterAI execution decision or risk score.
  • authorization_ttl_seconds · integer · optionnel
    Lifetime of a single-use execution authorization for a canonical action. Only Bearer-authenticated pilot requests receive executable authorization material.

  Exemple d'appel

  {"name": "oracle.verify_autonomous_action", "arguments": {"action": {}, "use_case": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"billed": {}, "result": {}}}

• oracle.verify_batch≈ 6192 tokens

  Use for multiple independent legacy or autonomous verification items in one authenticated prepaid call (1 to 100). The batch may consume account balance and records one trust receipt per item; InterAI does not execute any proposed external action. Reuse idempotency_key only for the same logical batch retry. For one proposed action, use oracle.verify_autonomous_action instead.

  Paramètres, retour & exemple (2)

  Paramètres

  • items · array · requis
    Independent verification items. Each item must contain either prompt + response or use_case + action; 1 to 100 items are accepted.
  • idempotency_key · string · optionnel
    Stable caller-provided key for retrying the same billed verification without duplicating the economic operation. Reuse it only for the same logical request.

  Exemple d'appel

  {"name": "oracle.verify_batch", "arguments": {"items": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"billed": {}, "oracle": {}, "results": [], "summary": {}, "batch_size": 1}}

• oracle.verify_response≈ 6269 tokens

  Legacy compatibility entry point for existing clients. This authenticated prepaid verification may consume account balance and records a trust receipt, but it does not execute any proposed external action. Supply exactly one contract: prompt + response, or use_case + action; never mix them. Reuse idempotency_key only for the same logical retry. For new action preflight use oracle.verify_autonomous_action; use oracle.verify_batch for multiple items.

  Paramètres, retour & exemple (12)

  Paramètres

  • mode · string · optionnel · fast_heuristic | semantic_judge
    Verification mode. Use fast_heuristic for the default low-latency path or semantic_judge when a semantic model judgment is explicitly required.
  • action · object · optionnel
    The proposed action. For executable pilot authorization use interai-canonical-action/v1 with host-registry tool_id, type, operation, exact arguments, and explicit side-effect semantics.
  • domain · string · optionnel
    Optional domain label used to provide verification context. It does not replace the exact action, context, or policy inputs.
  • policy · object · optionnel
    Optional strictly validated caller-scoped restrictions. They may tighten the boundary but cannot weaken host or account policy.
  • prompt · string · optionnel
    Legacy compatibility input: the original prompt whose response is being verified. Use together with response, not with autonomous action fields.
  • context · object · optionnel
    Optional runtime context surrounding the proposed action, such as environment, agent identity, counterparty, user confirmation, or other facts relevant to this decision.
  • response · string · optionnel
    Legacy compatibility input: the response to evaluate against prompt. Use together with prompt, not with autonomous action fields.
  • use_case · string · optionnel
    Stable identifier describing why the exact autonomous action is being proposed. Required together with action for the autonomous_execution contract.
  • idempotency_key · string · optionnel
    Stable caller-provided key for retrying the same billed verification without duplicating the economic operation. Reuse it only for the same logical request.
  • execution_context · object · optionnel
    Host-attested execution context bound to a canonical action. InterAI authenticates the account, not the truth of host-provided workspace, actor, run, or environment values.
  • external_evidence · array · optionnel
    Optional signed or verifiable external assertions. Current Stage 2 evidence is parsed, verified, bound, and recorded as non-authoritative evidence; it does not directly determine the InterAI execution decision or risk score.
  • authorization_ttl_seconds · integer · optionnel
    Lifetime of a single-use execution authorization for a canonical action. Only Bearer-authenticated pilot requests receive executable authorization material.

  Exemple d'appel

  {"name": "oracle.verify_response", "arguments": {"mode": "fast_heuristic", "action": {}, "domain": "texte", "policy": {}, "prompt": "texte", "context": {}}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"billed": {}, "result": {}}}

• oracle.verify_trust_receipt_signature≈ 676 tokens

  Read-only service-side validation of a trust receipt that already exists. Supply signature plus either receipt_id for the canonical server-stored receipt or a caller-supplied receipt object. Returns valid true or false when signing is enabled. Current signatures use HMAC-SHA256 and are service-verifiable by InterAI, not independent offline public-key proofs. It does not evaluate risk or create a receipt; use oracle.get_trust_receipt to retrieve receipt metadata.

  Paramètres, retour & exemple (5)

  Paramètres

  • receipt · object · optionnel
    Optional caller-supplied receipt object, typically evidence received from another agent or system. Either receipt or receipt_id is required.
  • signature · string · requis
    HMAC-SHA256 signature to validate against the referenced InterAI receipt. Required.
  • receipt_id · string · optionnel
    Optional ID of an existing InterAI trust receipt. InterAI resolves the canonical server-stored record before validating the supplied signature. Either receipt_id or receipt is required.
  • signature_alg · string · optionnel · hmac-sha256
    Optional signature algorithm declaration. The current supported value is hmac-sha256.
  • signed_payload · string · optionnel
    Optional exact serialized payload that was signed. Supply it when validating externally transported receipt evidence that includes the original signed payload.

  Exemple d'appel

  {"name": "oracle.verify_trust_receipt_signature", "arguments": {"signature": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"valid": true, "signature_alg": "hmac-sha256"}}

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://api.interailabs.dev/mcp