AgentStamp

import { requireStamp } from 'agentstamp-verify/express'; // Gate your API behind AgentStamp verification app.use('/api/', requireStamp({ minTier: 'bronze', x402: true }));

- Min delegator score:50
- Max outgoing delegations:5 per agent
- Expiry:30 days (auto-revoked)
- Bonus formula:delegator_score weight * 0.15, capped at 20 total points from all delegations

POST /api/v1/trust/delegate { delegatee_wallet, weight (0.1-2.0), reason } DELETE /api/v1/trust/delegate/:delegateeWallet GET /api/v1/trust/delegations/:wallet

Example: An agent with score 80 delegates with weight 1.0 = +12 points for the delegatee.

Human Sponsor & EU AI Act Compliance

Human Sponsor— Optionalhuman_sponsorfield (email or URL) on agent registration linking the agent to its human operator. Appears in passport, MCP tools, and compliance reports.

AI Act Fields— Optionalai_act_risk_level(minimal/limited/high) andtransparency_declaration(structured JSON: purpose, model_provider, training_data, human_oversight, data_retention).

Returns structured metadata for EU AI Act Article 52 transparency, including risk level, human sponsor, audit chain integrity, and trust status. Also available as MCP toolcompliance_report.

If a private key is compromised or needs rotation:

POST /api/v1/stamp/revoke/:stampId { reason: "key_rotation" | "key_compromise" | "decommissioned" | "owner_request" }

After revoking, mint a new stamp with the new wallet to complete the rotation. The old stamp is permanently revoked and the event is recorded in the audit trail.

Export any agent's passport as a W3C VC Data Model 2.0 credential:

Returns a standardVerifiableCredentialwithAgentTrustCredentialtype, interoperable with any W3C VC verifier. Issuer:did:web:agentstamp.org. Also available as MCP toolget_verifiable_credential.

Make your agent discoverable via DNS by adding a TXT record:

_agentstamp.yourdomain.com TXT "v=as1; wallet=0x...; stamp=gold"

Verify with:GET /api/v1/discovery/dns/yourdomain.com

Generate your TXT record:GET /api/v1/discovery/txt-record/:walletAddress

Also available as MCP tooldns_discovery.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Agent identity and trust framework — DID verification, capability attestation, agent-to-agent authentication by MEOK AI Labs

Cryptographic identity, scoped delegation, values governance, and deliberative consensus for AI agents. 11 tools, Ed25519 signatures, zero blockchain.

A secure MCP server for AI agents to interact with the Authenticator App for 2FA codes and passwords.

Agent identity and key custody — provider keys held in a local encrypted vault and leased to agents under owner approvals, with env-var injection so secrets never enter model context and a one-command kill switch; plus a registry with Ed25519 agent identity, reputation, and messaging.

Identity, secrets, and audit for AI agents. Proxy mode intercepts every MCP tool call.

Open-source API gateway that adds budget enforcement, cost attribution, and monetization to AI agent API calls. MCP-aware with per-tool cost tracking, macaroon-based bearer tokens, L402 Lightning micropayments, and enterprise budget control (Fiat402). The economic firewall for the agent economy.

ALTER - identity infrastructure for the AI economy

Auth0, but for agents. Identity and authentication service for AI agents.

AgentTrust is a pure MCP-only reputation and trust scoring server for AI agents.