HiveTrust

srotzin/hivetrust

If you're building autonomous agents that need to transact with each other, this gives you the identity and reputation infrastructure to make it safe. It exposes KYA verification endpoints for issuing DIDs and W3C credentials, a trust scoring engine that combines transaction history with staked capital and network centrality, and parametric insurance APIs for quoting and binding coverage before high-value tasks execute. The verify_agent_risk endpoint is designed to be called inline before your agent accepts an inbound request from a stranger. Think of it as a credit bureau and underwriter rolled into one REST service, meant to sit beneath a task execution runtime like HiveAgent.

tools: 17
transport: HTTP
last updated: Apr 14, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://hivetrust.onrender.com/mcp --name hivetrust

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http hivetrust https://hivetrust.onrender.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 17 tools

Verified live against the running server on Nov 6, 2026.

hivetrust_register_agentRegister 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.16 params

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* required

capabilitiesarray

List of capability tags (e.g. ["finance", "trading", "research"])

checksumstring

SHA-256 checksum of the agent (system prompt + tools + model config)

delegation_scopearray

Scope of delegated authority

descriptionstring

What this agent does

eu_ai_act_classstring

EU AI Act risk classificationone of minimal_risk · limited_risk · high_risk · unacceptable_riskdefault: minimal_risk

hiveagent_idstring

Cross-reference ID from HiveAgent platform

metadataobject

Additional key-value metadata

model_namestring

e.g. gpt-4o, claude-3-5-sonnet

model_providerstring

e.g. openai, anthropic, google

model_versionstring

Specific model version

name*string

Human-readable agent name

owner_id*string

ID of the owning organization or user

owner_typestring

one of organization · individual · daodefault: organization

public_keystring

Ed25519 public key (base58 encoded)

public_key_formatstring

Encoding format of the public keyone of ed25519-base58 · ed25519-hex · jwkdefault: ed25519-base58

verticalsarray

Industry verticals this agent operates in

hivetrust_get_agentRetrieve a registered agent's full identity profile, including public key, checksum, trust tier, capabilities, and compliance status.1 params

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

Parameters* required

agent_id*string

Agent UUID or DID (e.g. "did:hivetrust:abc123")

hivetrust_verify_identityVerify an agent's cryptographic identity by checking public key ownership and checksum integrity. Returns a verification result with confidence score and reason codes.4 params

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* required

agent_id*string

Agent UUID or DID to verify

challengestring

Optional challenge string to verify live key possession

checksumstring

Current agent checksum to compare against registered value

signaturestring

Agent's signature of the challenge (base58 encoded)

hivetrust_get_trust_scoreRetrieve 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.1 params

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* required

agent_id*string

Agent UUID or DID

hivetrust_verify_agent_riskQuick 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.1 params

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* required

agent_id*string

Agent UUID or DID to assess

hivetrust_ingest_telemetryBulk 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.1 params

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* required

events*array

Array of behavioral events to ingest

hivetrust_issue_credentialIssue a W3C-compatible verifiable credential to an agent. Credentials represent verified claims such as identity verification, compliance certification, or domain expertise.5 params

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

Parameters* required

agent_id*string

Agent UUID to issue the credential to

claims*object

Credential claims (key-value pairs specific to the credential type)

credential_type*string

Type of verifiable credentialone of

IdentityVerification · ComplianceCertification · DomainExpertise · CapitalVerification · HumanOversight · ThirdPartyAudit

expires_atstring

ISO 8601 expiration date (optional)

issuer_id*string

ID of the issuing entity

hivetrust_verify_credentialVerify a previously issued verifiable credential. Checks signature validity, revocation status, and expiration.1 params

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

Parameters* required

credential_id*string

UUID of the credential to verify

hivetrust_revoke_credentialRevoke a verifiable credential. Records the revocation in the registry. Revoked credentials immediately fail verification checks.4 params

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

Parameters* required

agent_idstring

Agent UUID that owns the credential

credential_id*string

UUID of the credential to revoke

evidenceobject

Supporting evidence for the revocation

reason*string

Reason for revocation (e.g. "compromised_key", "expired_compliance")

hivetrust_get_insurance_quoteGet 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.3 params

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* required

agent_id*string

Agent UUID being insured

counterparty_idstring

ID of the counterparty agent or user (optional)

transaction_value*number

Value of the transaction in USDC

hivetrust_bind_insuranceBind (activate) an insurance policy for an agent. Locks in the premium, creates the policy record, and deploys the escrow contract on Base L2.3 params

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* required

agent_id*string

Agent UUID to insure

quote_detailsobject

Quote object returned by hivetrust_get_insurance_quote

transaction_value*number

Transaction value in USDC

hivetrust_file_claimFile an insurance claim against an active policy. Triggers claims adjudication workflow. Payouts are made in USDC via the Base L2 escrow contract.6 params

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

Parameters* required

amount*number

Claim amount in USDC

claim_type*string

Type of claim being filedone of non_delivery · fraud · sla_breach · data_loss · unauthorized_action

claimant_id*string

ID of the entity filing the claim

descriptionstring

Detailed description of the claim

evidenceobject

Supporting evidence (transaction IDs, logs, screenshots)

policy_id*string

Insurance policy UUID

hivetrust_file_disputeFile a dispute or appeal against a trust score decision, credential revocation, or behavioral event. Initiates the dispute resolution workflow.6 params

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

Parameters* required

agent_id*string

Agent UUID filing the dispute

dispute_type*string

Category of the disputeone of score_dispute · credential_dispute · event_dispute · policy_dispute

evidenceobject

Supporting evidence for the dispute

reason*string

Detailed reason for the dispute

target_id*string

UUID of the resource being disputed

target_type*string

Type of the resource being disputedone of trust_score · credential · behavioral_event · insurance_policy · insurance_claim

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

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

No parameters. Call it with no arguments.

hivetrust_create_leaseCreate 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, co...3 params

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, co...

Parameters* required

data_stream*string

The data stream to lease access toone of construction_pricing · simpson_catalog · compliance_feeds · market_data · pheromone_signals

duration_hours*number

Lease duration in hours (24h, 72h, or 168h / 1 week)one of 24 · 72 · 168

lessee_did*string

DID of the agent acquiring the lease (e.g. "did:hivetrust:abc123")

hivetrust_stake_bondStake 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 yi...4 params

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 yi...

Parameters* required

agent_did*string

DID of the agent staking (e.g. "did:hive:abc123")

amount_usdc*number

Amount of USDC to stake. Must meet tier minimum: bronze $100, silver $500, gold $2000, platinum $10000.

lock_period_days*number

Lock period in days. Longer lock = higher APY: 30d 2%, 90d 3%, 180d 4%, 365d 5%.one of 30 · 90 · 180 · 365

tier*string

Bond tier. Determines max bounty access: bronze $1k, silver $10k, gold $50k, platinum unlimited.one of bronze · silver · gold · platinum

hivetrust_verify_bondQuick 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, n...1 params

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, n...

Parameters* required

did*string

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

Readme

🐝 HiveTrust

██╗  ██╗██╗██╗   ██╗███████╗████████╗██████╗ ██╗   ██╗███████╗████████╗
██║  ██║██║██║   ██║██╔════╝╚══██╔══╝██╔══██╗██║   ██║██╔════╝╚══██╔══╝
███████║██║██║   ██║█████╗     ██║   ██████╔╝██║   ██║███████╗   ██║   
██╔══██║██║╚██╗ ██╔╝██╔══╝     ██║   ██╔══██╗██║   ██║╚════██║   ██║   
██║  ██║██║ ╚████╔╝ ███████╗   ██║   ██║  ██║╚██████╔╝███████║   ██║   
╚═╝  ╚═╝╚═╝  ╚═══╝  ╚══════╝   ╚═╝   ╚═╝  ╚═╝ ╚═════╝ ╚══════╝   ╚═╝

"The Equifax + GEICO of the A2A Economy"

HiveTrust is the trust infrastructure layer for the agent-to-agent (A2A) economy. It provides Know-Your-Agent (KYA) identity verification, algorithmic trust scoring, and parametric insurance so that AI agents can transact with each other safely — at machine speed, without human intermediaries.

View the full README on GitHub

Details

Repository: github.com/srotzin/hivetrust
Website: www.hiveagentiq.com
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

HiveTrust

Install

Tools

Readme

🐝 HiveTrust

Details

More from srotzin