HiveTrust

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

KYA identity verification, trust scoring, and performance bonds for AI agents

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "HiveTrust": {
      "url": "https://hivetrust.onrender.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (17)

• hivetrust_register_agent

  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.

  Parameters:

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

  Hints: read-only no · destructive no · idempotent no · open-world not declared

• hivetrust_get_agent read-only

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

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• hivetrust_verify_identity read-only

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

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• hivetrust_get_trust_score read-only

  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.

  Parameters:

  • agent_id (required) — string — Agent UUID or DID

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• hivetrust_verify_agent_risk read-only

  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.

  Parameters:

  • agent_id (required) — string — Agent UUID or DID to assess

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• hivetrust_ingest_telemetry

  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.

  Parameters:

  • events (required) — array — Array of behavioral events to ingest

  Hints: read-only no · destructive no · idempotent no · open-world not declared

• hivetrust_issue_credential

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

  Parameters:

  • agent_id (required) — string — Agent UUID to issue the credential to
  • credential_type (required) — string — Type of verifiable credential
  • issuer_id (required) — string — ID of the issuing entity
  • claims (required) — object — Credential claims (key-value pairs specific to the credential type)
  • expires_at — string — ISO 8601 expiration date (optional)

  Hints: read-only no · destructive no · idempotent no · open-world not declared

• hivetrust_verify_credential read-only

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

  Parameters:

  • credential_id (required) — string — UUID of the credential to verify

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• hivetrust_revoke_credential destructive

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

  Parameters:

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

  Hints: read-only no · destructive yes · idempotent no · open-world not declared

• hivetrust_get_insurance_quote read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent no · open-world not declared

• hivetrust_bind_insurance

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

  Parameters:

  • agent_id (required) — string — Agent UUID to insure
  • transaction_value (required) — number — Transaction value in USDC
  • quote_details — object — Quote object returned by hivetrust_get_insurance_quote

  Hints: read-only no · destructive no · idempotent no · open-world not declared

• hivetrust_file_claim

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

  Parameters:

  • policy_id (required) — string — Insurance policy UUID
  • claimant_id (required) — string — ID of the entity filing the claim
  • claim_type (required) — string — Type of claim being filed
  • amount (required) — number — Claim amount in USDC
  • evidence — object — Supporting evidence (transaction IDs, logs, screenshots)
  • description — string — Detailed description of the claim

  Hints: read-only no · destructive no · idempotent no · open-world not declared

• hivetrust_file_dispute

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

  Parameters:

  • agent_id (required) — string — Agent UUID filing the dispute
  • dispute_type (required) — string — Category of the dispute
  • target_type (required) — string — Type of the resource being disputed
  • target_id (required) — string — UUID of the resource being disputed
  • reason (required) — string — Detailed reason for the dispute
  • evidence — object — Supporting evidence for the dispute

  Hints: read-only no · destructive no · idempotent no · open-world not declared

• hivetrust_get_platform_stats read-only

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

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

• hivetrust_create_lease

  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.

  Parameters:

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

  Hints: read-only no · destructive no · idempotent no · open-world not declared

• hivetrust_stake_bond

  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.

  Parameters:

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

  Hints: read-only no · destructive no · idempotent no · open-world not declared

• hivetrust_verify_bond read-only

  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.

  Parameters:

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

  Hints: read-only yes · destructive no · idempotent yes · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.