MCP Server
HiveTrust
io.github.srotzin/hivetrust
What this MCP does
Registers and verifies AI agent identities, credentials, trust scores, bonds, insurance, compliance status, and transaction risk.
Capabilities
Tools
17
tools
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.
Input schema
{'type': 'object', 'required': ['agent_id', 'transaction_value'], 'properties': {'agent_id': {'type': 'string', 'description': 'Agent UUID to insure'}, 'quote_details': {'type': 'object', 'description': 'Quote object returned by hivetrust_get_insurance_quote'}, 'transaction_value': {'type': 'number', 'minimum': 0, 'description': 'Transaction value in USDC'}}}
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.
Input schema
{'type': 'object', 'required': ['lessee_did', 'data_stream', 'duration_hours'], 'properties': {'lessee_did': {'type': 'string', 'description': 'DID of the agent acquiring the lease (e.g. "did:hivetrust:abc123")'}, 'data_stream': {'enum': ['construction_pricing', 'simpson_catalog', 'compliance_feeds', 'market_data', 'pheromone_signals'], 'type': 'string', 'description': 'The data stream to lease access to'}, 'duration_hours': {'enum': [24, 72, 168], 'type': 'number', 'description': 'Lease duration in hours (24h, 72h, or 168h / 1 week)'}}}
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.
Input schema
{'type': 'object', 'required': ['policy_id', 'claimant_id', 'claim_type', 'amount'], 'properties': {'amount': {'type': 'number', 'minimum': 0, 'description': 'Claim amount in USDC'}, 'evidence': {'type': 'object', 'description': 'Supporting evidence (transaction IDs, logs, screenshots)'}, 'policy_id': {'type': 'string', 'description': 'Insurance policy UUID'}, 'claim_type': {'enum': ['non_delivery', 'fraud', 'sla_breach', 'data_loss', 'unauthorized_action'], 'type': 'string', 'description': 'Type of claim being filed'}, 'claimant_id': {'type': 'string', 'description': 'ID of the entity filing the claim'}, 'description': {'type': 'string', 'description': 'Detailed description of the claim'}}}
hivetrust_file_dispute
File a dispute or appeal against a trust score decision, credential revocation, or behavioral event. Initiates the dispute resolution workflow.
Input schema
{'type': 'object', 'required': ['agent_id', 'dispute_type', 'target_type', 'target_id', 'reason'], 'properties': {'reason': {'type': 'string', 'description': 'Detailed reason for the dispute'}, 'agent_id': {'type': 'string', 'description': 'Agent UUID filing the dispute'}, 'evidence': {'type': 'object', 'description': 'Supporting evidence for the dispute'}, 'target_id': {'type': 'string', 'description': 'UUID of the resource being disputed'}, 'target_type': {'enum': ['trust_score', 'credential', 'behavioral_event', 'insurance_policy', 'insurance_claim'], 'type': 'string', 'description': 'Type of the resource being disputed'}, 'dispute_type': {'enum': ['score_dispute', 'credential_dispute', 'event_dispute', 'policy_dispute'], 'type': 'string', 'description': 'Category of the dispute'}}}
hivetrust_get_agent
Retrieve a registered agent's full identity profile, including public key, checksum, trust tier, capabilities, and compliance status.
Read only
Idempotent
Input schema
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Agent UUID or DID (e.g. "did:hivetrust:abc123")'}}}
hivetrust_get_insurance_quote
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.
Read only
Input schema
{'type': 'object', 'required': ['agent_id', 'transaction_value'], 'properties': {'agent_id': {'type': 'string', 'description': 'Agent UUID being insured'}, 'counterparty_id': {'type': 'string', 'description': 'ID of the counterparty agent or user (optional)'}, 'transaction_value': {'type': 'number', 'minimum': 0, 'description': 'Value of the transaction in USDC'}}}
hivetrust_get_platform_stats
Retrieve HiveTrust platform-wide statistics: total registered agents, verified count, average trust score, total insured value, active policies, claims filed, and more.
Read only
Idempotent
Input schema
{'type': 'object', 'required': [], 'properties': {}}
hivetrust_get_trust_score
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.
Read only
Idempotent
Input schema
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Agent UUID or DID'}}}
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.
Input schema
{'type': 'object', 'required': ['events'], 'properties': {'events': {'type': 'array', 'items': {'type': 'object', 'required': ['agent_id', 'event_type', 'source'], 'properties': {'action': {'type': 'string', 'description': 'Specific action performed'}, 'source': {'type': 'string', 'description': 'Platform or system emitting the event'}, 'outcome': {'enum': ['success', 'failure', 'partial', 'disputed'], 'type': 'string', 'description': 'Outcome of the action'}, 'agent_id': {'type': 'string', 'description': 'Agent UUID'}, 'evidence': {'type': 'object', 'description': 'Supporting evidence for the event'}, 'metadata': {'type': 'object', 'description': 'Additional event metadata'}, 'event_type': {'enum': ['transaction_completed', 'transaction_failed', 'sla_violation', 'dispute_filed', 'dispute_resolved', 'tool_call', 'auth_success', 'auth_failure', 'checksum_mismatch', 'fidelity_probe', 'capital_staked', 'capital_withdrawn'], 'type': 'string', 'description': 'Type of behavioral event'}, 'counterparty_id': {'type': 'string', 'description': 'ID of the other party in the transaction'}, 'source_platform': {'type': 'string', 'description': 'Platform name'}, 'transaction_value': {'type': 'number', 'description': 'Transaction value in USDC'}}}, 'description': 'Array of behavioral events to ingest'}}}
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.
Input schema
{'type': 'object', 'required': ['agent_id', 'credential_type', 'issuer_id', 'claims'], 'properties': {'claims': {'type': 'object', 'description': 'Credential claims (key-value pairs specific to the credential type)'}, 'agent_id': {'type': 'string', 'description': 'Agent UUID to issue the credential to'}, 'issuer_id': {'type': 'string', 'description': 'ID of the issuing entity'}, 'expires_at': {'type': 'string', 'format': 'date-time', 'description': 'ISO 8601 expiration date (optional)'}, 'credential_type': {'enum': ['IdentityVerification', 'ComplianceCertification', 'DomainExpertise', 'CapitalVerification', 'HumanOversight', 'ThirdPartyAudit'], 'type': 'string', 'description': 'Type of verifiable credential'}}}
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.
Input schema
{'type': 'object', 'required': ['name', 'owner_id'], 'properties': {'name': {'type': 'string', 'description': 'Human-readable agent name'}, 'checksum': {'type': 'string', 'description': 'SHA-256 checksum of the agent (system prompt + tools + model config)'}, 'metadata': {'type': 'object', 'description': 'Additional key-value metadata'}, 'owner_id': {'type': 'string', 'description': 'ID of the owning organization or user'}, 'verticals': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Industry verticals this agent operates in'}, 'model_name': {'type': 'string', 'description': 'e.g. gpt-4o, claude-3-5-sonnet'}, 'owner_type': {'enum': ['organization', 'individual', 'dao'], 'type': 'string', 'default': 'organization'}, 'public_key': {'type': 'string', 'description': 'Ed25519 public key (base58 encoded)'}, 'description': {'type': 'string', 'description': 'What this agent does'}, 'capabilities': {'type': 'array', 'items': {'type': 'string'}, 'description': 'List of capability tags (e.g. ["finance", "trading", "research"])'}, 'hiveagent_id': {'type': 'string', 'description': 'Cross-reference ID from HiveAgent platform'}, 'model_version': {'type': 'string', 'description': 'Specific model version'}, 'model_provider': {'type': 'string', 'description': 'e.g. openai, anthropic, google'}, 'eu_ai_act_class': {'enum': ['minimal_risk', 'limited_risk', 'high_risk', 'unacceptable_risk'], 'type': 'string', 'default': 'minimal_risk', 'description': 'EU AI Act risk classification'}, 'delegation_scope': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Scope of delegated authority'}, 'public_key_format': {'enum': ['ed25519-base58', 'ed25519-hex', 'jwk'], 'type': 'string', 'default': 'ed25519-base58', 'description': 'Encoding format of the public key'}}}
hivetrust_revoke_credential
Revoke a verifiable credential. Records the revocation in the registry. Revoked credentials immediately fail verification checks.
Destructive
Input schema
{'type': 'object', 'required': ['credential_id', 'reason'], 'properties': {'reason': {'type': 'string', 'description': 'Reason for revocation (e.g. "compromised_key", "expired_compliance")'}, 'agent_id': {'type': 'string', 'description': 'Agent UUID that owns the credential'}, 'evidence': {'type': 'object', 'description': 'Supporting evidence for the revocation'}, 'credential_id': {'type': 'string', 'description': 'UUID of the credential to revoke'}}}
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.
Input schema
{'type': 'object', 'required': ['agent_did', 'amount_usdc', 'tier', 'lock_period_days'], 'properties': {'tier': {'enum': ['bronze', 'silver', 'gold', 'platinum'], 'type': 'string', 'description': 'Bond tier. Determines max bounty access: bronze $1k, silver $10k, gold $50k, platinum unlimited.'}, 'agent_did': {'type': 'string', 'description': 'DID of the agent staking (e.g. "did:hive:abc123")'}, 'amount_usdc': {'type': 'number', 'minimum': 100, 'description': 'Amount of USDC to stake. Must meet tier minimum: bronze $100, silver $500, gold $2000, platinum $10000.'}, 'lock_period_days': {'enum': [30, 90, 180, 365], 'type': 'number', 'description': 'Lock period in days. Longer lock = higher APY: 30d 2%, 90d 3%, 180d 4%, 365d 5%.'}}}
hivetrust_verify_agent_risk
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.
Read only
Idempotent
Input schema
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Agent UUID or DID to assess'}}}
hivetrust_verify_bond
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.
Read only
Idempotent
Input schema
{'type': 'object', 'required': ['did'], 'properties': {'did': {'type': 'string', 'description': 'DID of the agent to verify (e.g. "did:hive:abc123")'}}}
hivetrust_verify_credential
Verify a previously issued verifiable credential. Checks signature validity, revocation status, and expiration.
Read only
Idempotent
Input schema
{'type': 'object', 'required': ['credential_id'], 'properties': {'credential_id': {'type': 'string', 'description': 'UUID of the credential to verify'}}}
hivetrust_verify_identity
Verify an agent's cryptographic identity by checking public key ownership and checksum integrity. Returns a verification result with confidence score and reason codes.
Read only
Idempotent
Input schema
{'type': 'object', 'required': ['agent_id'], 'properties': {'agent_id': {'type': 'string', 'description': 'Agent UUID or DID to verify'}, 'checksum': {'type': 'string', 'description': 'Current agent checksum to compare against registered value'}, 'challenge': {'type': 'string', 'description': 'Optional challenge string to verify live key possession'}, 'signature': {'type': 'string', 'description': "Agent's signature of the challenge (base58 encoded)"}}}
History
Recent tool changes
Added
hivetrust_verify_bond
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_stake_bond
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_create_lease
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_get_platform_stats
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_file_dispute
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_file_claim
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_bind_insurance
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_get_insurance_quote
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_revoke_credential
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_verify_credential
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_issue_credential
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_ingest_telemetry
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_verify_agent_risk
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_get_trust_score
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_verify_identity
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_get_agent
Sept. 17, 2026, 12:52 p.m.
Added
hivetrust_register_agent
Sept. 17, 2026, 12:52 p.m.
Discover
Similar MCP servers
mainstreet
io.github.philpof102-svg/mainstreet
Provides reputation, trust scoring, validation, consensus, routing, and payment-related tools for on-chain AI agents on Base.
DCL Trust Oracle — AI/LLM Output Audit (x402 MCP)
com.fronesislabs/dcl-trust-oracle
Audits AI and agent outputs for jailbreaks, secrets, PII, unsafe trading language, and quality issues, and records cryptographica…
GoCreative Agent API
io.github.ColinHughes2121/gocreative-agent-api
Offers pay-per-call LLM completions and data services for company intelligence, KYB, sanctions screening, threat intelligence, co…
IA-QA — 130+ QA & Dev Tools for AI Agents
io.github.JcJamet/ia-qa-toolbox
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
Crypto Bot Audit + Market Data (x402 paid)
io.github.kaminariouji/x402-audit-agent
Audits crypto bot source code and provides paid crypto market, token, gas, stablecoin, and DeFi TVL data.
AgentBIT
app.agentbit/mcp
Routes pay-per-call tools over x402 on Base, covering discovery, data conversion, company research, counterparty screening, domai…
Robyn — Gasless Cross-Chain for AI Agents
io.github.ox31461/robyn
Supports gasless cross-chain transfers, wallet and transaction checks, spending mandates, privacy-preserving messaging, and signe…
Polyform
org.polyform/polyform
Offers pay-per-call APIs for economic, financial, geographic, healthcare, domain, email, sanctions, blockchain, and business risk…