io.github.srotzin/hivetrust

Est-ce que io.github.srotzin/hivetrust est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.srotzin/hivetrust » 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 17 outils

• hivetrust_bind_insurance≈ 166 tokens

  Bind (activate) an insurance policy for an agent. Locks in the premium, creates the policy record, and deploys the escrow contract on Base L2.

  Paramètres, retour & exemple (3)

  Paramètres

  • agent_id · string · requis
    Agent UUID to insure
  • quote_details · object · optionnel
    Quote object returned by hivetrust_get_insurance_quote
  • transaction_value · number · requis
    Transaction value in USDC

  Exemple d'appel

  {"name": "hivetrust_bind_insurance", "arguments": {"agent_id": "texte", "transaction_value": 1}}

  Exemple de retour

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

• hivetrust_create_lease≈ 258 tokens

  Create a Data Oracle Context Lease — "Sign Once, Settle Many". Grants unlimited access to a data stream for a fixed period (24h/72h/168h). Returns a cryptographic lease token (SHA-256) for zero-friction verification. Available streams: construction_pricing, simpson_catalog, compliance_feeds, market_data, pheromone_signals.

  Paramètres, retour & exemple (3)

  Paramètres

  • lessee_did · string · requis
    DID of the agent acquiring the lease (e.g. "did:hivetrust:abc123")
  • data_stream · string · requis · construction_pricing | simpson_catalog | compliance_feeds | market_data | pheromone_signals
    The data stream to lease access to
  • duration_hours · number · requis · 24 | 72 | 168
    Lease duration in hours (24h, 72h, or 168h / 1 week)

  Exemple d'appel

  {"name": "hivetrust_create_lease", "arguments": {"lessee_did": "texte", "data_stream": "construction_pricing", "duration_hours": 24}}

  Exemple de retour

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

• hivetrust_file_claim≈ 251 tokens

  File an insurance claim against an active policy. Triggers claims adjudication workflow. Payouts are made in USDC via the Base L2 escrow contract.

  Paramètres, retour & exemple (6)

  Paramètres

  • amount · number · requis
    Claim amount in USDC
  • evidence · object · optionnel
    Supporting evidence (transaction IDs, logs, screenshots)
  • policy_id · string · requis
    Insurance policy UUID
  • claim_type · string · requis · non_delivery | fraud | sla_breach | data_loss | unauthorized_action
    Type of claim being filed
  • claimant_id · string · requis
    ID of the entity filing the claim
  • description · string · optionnel
    Detailed description of the claim

  Exemple d'appel

  {"name": "hivetrust_file_claim", "arguments": {"amount": 1, "policy_id": "texte", "claim_type": "non_delivery", "claimant_id": "texte"}}

  Exemple de retour

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

• hivetrust_file_dispute≈ 275 tokens

  File a dispute or appeal against a trust score decision, credential revocation, or behavioral event. Initiates the dispute resolution workflow.

  Paramètres, retour & exemple (6)

  Paramètres

  • reason · string · requis
    Detailed reason for the dispute
  • agent_id · string · requis
    Agent UUID filing the dispute
  • evidence · object · optionnel
    Supporting evidence for the dispute
  • target_id · string · requis
    UUID of the resource being disputed
  • target_type · string · requis · trust_score | credential | behavioral_event | insurance_policy | insurance_claim
    Type of the resource being disputed
  • dispute_type · string · requis · score_dispute | credential_dispute | event_dispute | policy_dispute
    Category of the dispute

  Exemple d'appel

  {"name": "hivetrust_file_dispute", "arguments": {"reason": "texte", "agent_id": "texte", "target_id": "texte", "target_type": "trust_score", "dispute_type": "score_dispute"}}

  Exemple de retour

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

• hivetrust_get_agent≈ 112 tokens

  Retrieve a registered agent's full identity profile, including public key, checksum, trust tier, capabilities, and compliance status.

  Paramètres, retour & exemple (1)

  Paramètres

  • agent_id · string · requis
    Agent UUID or DID (e.g. "did:hivetrust:abc123")

  Exemple d'appel

  {"name": "hivetrust_get_agent", "arguments": {"agent_id": "texte"}}

  Exemple de retour

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

• hivetrust_get_insurance_quote≈ 182 tokens

  Get a dynamic insurance premium quote for an agent transaction. Premium is calculated based on trust score, transaction value, and risk tier. HiveTrust takes a 1.5% spread on insured transactions.

  Paramètres, retour & exemple (3)

  Paramètres

  • agent_id · string · requis
    Agent UUID being insured
  • counterparty_id · string · optionnel
    ID of the counterparty agent or user (optional)
  • transaction_value · number · requis
    Value of the transaction in USDC

  Exemple d'appel

  {"name": "hivetrust_get_insurance_quote", "arguments": {"agent_id": "texte", "transaction_value": 1}}

  Exemple de retour

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

• hivetrust_get_platform_stats≈ 96 tokens

  Retrieve HiveTrust platform-wide statistics: total registered agents, verified count, average trust score, total insured value, active policies, claims filed, and more.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "hivetrust_get_platform_stats", "arguments": {}}

  Exemple de retour

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

• hivetrust_get_trust_score≈ 128 tokens

  Retrieve an agent's current multi-pillar trust score (0–1000 scale). Returns composite score, tier, per-pillar breakdown (identity, behavior, fidelity, compliance, provenance), verdict, and max recommended transaction value.

  Paramètres, retour & exemple (1)

  Paramètres

  • agent_id · string · requis
    Agent UUID or DID

  Exemple d'appel

  {"name": "hivetrust_get_trust_score", "arguments": {"agent_id": "texte"}}

  Exemple de retour

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

• hivetrust_ingest_telemetry≈ 416 tokens

  Bulk ingest behavioral telemetry events for an agent. These events feed into the trust scoring engine. Supports transaction completions, SLA violations, dispute events, tool calls, and more.

  Paramètres, retour & exemple (1)

  Paramètres

  • events · array · requis
    Array of behavioral events to ingest

  Exemple d'appel

  {"name": "hivetrust_ingest_telemetry", "arguments": {"events": []}}

  Exemple de retour

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

• hivetrust_issue_credential≈ 264 tokens

  Issue a W3C-compatible verifiable credential to an agent. Credentials represent verified claims such as identity verification, compliance certification, or domain expertise.

  Paramètres, retour & exemple (5)

  Paramètres

  • claims · object · requis
    Credential claims (key-value pairs specific to the credential type)
  • agent_id · string · requis
    Agent UUID to issue the credential to
  • issuer_id · string · requis
    ID of the issuing entity
  • expires_at · string · optionnel
    ISO 8601 expiration date (optional)
  • credential_type · string · requis · IdentityVerification | ComplianceCertification | DomainExpertise | CapitalVerification | HumanOversight | ThirdPartyAudit
    Type of verifiable credential

  Exemple d'appel

  {"name": "hivetrust_issue_credential", "arguments": {"claims": {}, "agent_id": "texte", "issuer_id": "texte", "credential_type": "IdentityVerification"}}

  Exemple de retour

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

• hivetrust_register_agent≈ 528 tokens

  Register a new AI agent identity with HiveTrust KYA (Know Your Agent). Assigns a unique agent ID, anchors the public key, and initializes the trust score.

  Paramètres, retour & exemple (16)

  Paramètres

  • name · string · requis
    Human-readable agent name
  • checksum · string · optionnel
    SHA-256 checksum of the agent (system prompt + tools + model config)
  • metadata · object · optionnel
    Additional key-value metadata
  • owner_id · string · requis
    ID of the owning organization or user
  • verticals · array · optionnel
    Industry verticals this agent operates in
  • model_name · string · optionnel
    e.g. gpt-4o, claude-3-5-sonnet
  • owner_type · string · optionnel · organization | individual | dao
  • public_key · string · optionnel
    Ed25519 public key (base58 encoded)
  • description · string · optionnel
    What this agent does
  • capabilities · array · optionnel
    List of capability tags (e.g. ["finance", "trading", "research"])
  • hiveagent_id · string · optionnel
    Cross-reference ID from HiveAgent platform
  • model_version · string · optionnel
    Specific model version
  • model_provider · string · optionnel
    e.g. openai, anthropic, google
  • eu_ai_act_class · string · optionnel · minimal_risk | limited_risk | high_risk | unacceptable_risk
    EU AI Act risk classification
  • delegation_scope · array · optionnel
    Scope of delegated authority
  • public_key_format · string · optionnel · ed25519-base58 | ed25519-hex | jwk
    Encoding format of the public key

  Exemple d'appel

  {"name": "hivetrust_register_agent", "arguments": {"name": "texte", "owner_id": "texte"}}

  Exemple de retour

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

• hivetrust_revoke_credential≈ 188 tokens

  Revoke a verifiable credential. Records the revocation in the registry. Revoked credentials immediately fail verification checks.

  Paramètres, retour & exemple (4)

  Paramètres

  • reason · string · requis
    Reason for revocation (e.g. "compromised_key", "expired_compliance")
  • agent_id · string · optionnel
    Agent UUID that owns the credential
  • evidence · object · optionnel
    Supporting evidence for the revocation
  • credential_id · string · requis
    UUID of the credential to revoke

  Exemple d'appel

  {"name": "hivetrust_revoke_credential", "arguments": {"reason": "texte", "credential_id": "texte"}}

  Exemple de retour

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

• hivetrust_stake_bond≈ 320 tokens

  Stake USDC to back an agent's reputation via HiveBond. Creates a trust bond with a specified tier (bronze/silver/gold/platinum) and lock period. Phase 1: declared stake amount tracked in-memory; flat $0.25 registration fee via x402. Longer lock periods earn higher simulated yield (2–5% APY). Slashing is permanent — if an agent fails, stake is slashed and paid to injured parties.

  Paramètres, retour & exemple (4)

  Paramètres

  • tier · string · requis · bronze | silver | gold | platinum
    Bond tier. Determines max bounty access: bronze $1k, silver $10k, gold $50k, platinum unlimited.
  • agent_did · string · requis
    DID of the agent staking (e.g. "did:hive:abc123")
  • amount_usdc · number · requis
    Amount of USDC to stake. Must meet tier minimum: bronze $100, silver $500, gold $2000, platinum $10000.
  • lock_period_days · number · requis · 30 | 90 | 180 | 365
    Lock period in days. Longer lock = higher APY: 30d 2%, 90d 3%, 180d 4%, 365d 5%.

  Exemple d'appel

  {"name": "hivetrust_stake_bond", "arguments": {"tier": "bronze", "agent_did": "texte", "amount_usdc": 1, "lock_period_days": 30}}

  Exemple de retour

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

• hivetrust_verify_agent_risk≈ 126 tokens

  Quick risk assessment for payment processors and marketplace operators. Returns verdict (ALLOW/REVIEW/BLOCK), trust tier, and max transaction limit. This is the free public endpoint — no API key required.

  Paramètres, retour & exemple (1)

  Paramètres

  • agent_id · string · requis
    Agent UUID or DID to assess

  Exemple d'appel

  {"name": "hivetrust_verify_agent_risk", "arguments": {"agent_id": "texte"}}

  Exemple de retour

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

• hivetrust_verify_bond≈ 153 tokens

  Quick bond verification — check if an agent is bonded and at what tier. Returns bonded status, tier, staked amount, slash count, and max bounty access. This is the key integration point — other services call this to check bond status before assigning bounties. Free endpoint, no x402 payment required.

  Paramètres, retour & exemple (1)

  Paramètres

  • did · string · requis
    DID of the agent to verify (e.g. "did:hive:abc123")

  Exemple d'appel

  {"name": "hivetrust_verify_bond", "arguments": {"did": "texte"}}

  Exemple de retour

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

• hivetrust_verify_credential≈ 107 tokens

  Verify a previously issued verifiable credential. Checks signature validity, revocation status, and expiration.

  Paramètres, retour & exemple (1)

  Paramètres

  • credential_id · string · requis
    UUID of the credential to verify

  Exemple d'appel

  {"name": "hivetrust_verify_credential", "arguments": {"credential_id": "texte"}}

  Exemple de retour

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

• hivetrust_verify_identity≈ 196 tokens

  Verify an agent's cryptographic identity by checking public key ownership and checksum integrity. Returns a verification result with confidence score and reason codes.

  Paramètres, retour & exemple (4)

  Paramètres

  • agent_id · string · requis
    Agent UUID or DID to verify
  • checksum · string · optionnel
    Current agent checksum to compare against registered value
  • challenge · string · optionnel
    Optional challenge string to verify live key possession
  • signature · string · optionnel
    Agent's signature of the challenge (base58 encoded)

  Exemple d'appel

  {"name": "hivetrust_verify_identity", "arguments": {"agent_id": "texte"}}

  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://hivetrust.onrender.com/mcp