Card snapshot

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "protocolVersion": "0.3.0",
  "name": "A-Identity Trust Oracle",
  "description": "Before one AI agent pays another, it calls A-Identity to verify the counterparty. Returns the counterparty's on-chain ERC-8004 identity and KYA status, a deterministic reputation score from 0 to 1000 computed from real settlements, and a single ALLOW, WARN or DENY verdict for the specific payment being considered. Every score is reproducible and every settlement it has taken is published with its transaction hash.",
  "version": "1.1.0",
  "url": "https://a-identity.xyz",
  "documentationUrl": "https://a-identity.xyz/llms-full.txt",
  "iconUrl": "https://a-identity.xyz/favicon.svg",
  "preferredTransport": "JSONRPC",
  "supportedInterfaces": [
    {
      "url": "https://a-identity.xyz/mcp",
      "transport": "JSONRPC",
      "protocol": "MCP",
      "description": "Model Context Protocol over Streamable HTTP. 19 tools covering identity, reputation, policy and hiring."
    },
    {
      "url": "https://a-identity-asp.onrender.com",
      "transport": "HTTP+JSON",
      "protocol": "x402",
      "description": "Pay-per-call HTTP tools. An unpaid request returns HTTP 402 with the payment requirements; the resource is served on a paid retry."
    }
  ],
  "provider": {
    "organization": "A-Identity",
    "url": "https://a-identity.xyz"
  },
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": true,
    "extensions": [
      {
        "uri": "https://x402.org",
        "description": "Payment is settled per call in USDC over x402. No account, no API key, no subscription.",
        "required": false
      },
      {
        "uri": "https://eips.ethereum.org/EIPS/eip-8004",
        "description": "Agent identity is an ERC-8004 on-chain passport, not a self-declared profile.",
        "required": false
      }
    ]
  },
  "defaultInputModes": [
    "application/json",
    "text/plain"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "securitySchemes": {
    "x402": {
      "type": "http",
      "scheme": "x402",
      "description": "Per-call payment in USDC. An unpaid request is answered with HTTP 402 and a machine-readable challenge carrying the price, the network, the asset and the address to pay."
    }
  },
  "skills": [
    {
      "id": "verify_agent",
      "name": "Verify an agent's identity",
      "description": "Returns an agent's on-chain ERC-8004 registration and its KYA status, which is the agent proving control of its own wallet, recorded on-chain rather than self-declared.",
      "tags": [
        "identity",
        "erc-8004",
        "kya",
        "verification"
      ],
      "examples": [
        "Is agent #849980 a real registered agent, and has it proved it controls its wallet?"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "reputation_score",
      "name": "Score an agent's reputation",
      "description": "A deterministic score from 0 to 1000 computed from real on-chain settlements, validation and tenure, with a recency decay and a Sybil check. The same inputs always produce the same score, and any caller can reproduce it from the published method.",
      "tags": [
        "reputation",
        "scoring",
        "on-chain",
        "deterministic"
      ],
      "examples": [
        "What is agent #849980's reputation, and what drove the number?"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "risk_check",
      "name": "Decide whether a payment should go through",
      "description": "A pre-transaction verdict on a counterparty: ALLOW, WARN or DENY, with the reasons that produced it. Takes the intended amount so the risk is sized to the payment rather than judged in the abstract.",
      "tags": [
        "risk",
        "payments",
        "pre-transaction",
        "policy"
      ],
      "examples": [
        "I am about to pay agent #849980 twenty five dollars. Should I?"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "counterparty_check",
      "name": "Check both sides of a proposed deal",
      "description": "Inspects the payer and the payee together, which is how it catches same-operator self-dealing that a one-sided scan cannot see.",
      "tags": [
        "risk",
        "counterparty",
        "self-dealing",
        "sybil"
      ],
      "examples": [
        "Agent #6271 wants to pay agent #849980. Are these actually the same operator?"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "guardrail_check",
      "name": "Check an action against its owner's limits",
      "description": "Runs the live policy engine over a proposed action and answers allow, ask a human, or block, naming the rule that decided it. Reports bands only: caps, allowlists and holdings are never disclosed.",
      "tags": [
        "policy",
        "guardrails",
        "spend-limits",
        "governance"
      ],
      "examples": [
        "Does this agent operate under an enforced spend policy, and does it respect the verdicts?"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "agent_passport",
      "name": "Fetch a full agent passport",
      "description": "Identity, KYA, reputation and risk in a single call, for when a caller wants the whole picture rather than one answer.",
      "tags": [
        "identity",
        "reputation",
        "risk",
        "passport"
      ],
      "examples": [
        "Give me everything you know about agent #849980."
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "trust_preview",
      "name": "Free coarse trust band",
      "description": "A free, rate-limited on-ramp returning a coarse trust band plus revoked and Sybil flags, so a caller can try the service before spending anything.",
      "tags": [
        "free",
        "preview",
        "trust"
      ],
      "examples": [
        "Give me a quick read on agent #849980 before I pay for the full check."
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    }
  ],
  "supportsAuthenticatedExtendedCard": false
}