TollWarden

{
  "protocolVersion": "0.3.0",
  "name": "TollWarden",
  "description": "Call this before your agent settles any x402 payment to check it for fraud. TollWarden answers 'is this payment safe to send?' and 'is this 402 offer safe to pay?' \u2014 catching payments to attacker-controlled addresses injected into content the agent just read (prompt-injection-triggered payments), replayed authorizations, overpayment vs the quote, secrets leaking through payment metadata, fake/lookalike USDC contracts, and address poisoning. Returns allow/flag/block with machine-readable reasons and an Ed25519-signed verdict a wallet can enforce. Non-custodial: never holds keys or funds; wraps whatever wallet/facilitator the agent already uses.",
  "url": "https://tollwarden.com",
  "provider": {
    "organization": "TollWarden",
    "url": "https://tollwarden.com"
  },
  "version": "1.6.0",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "skills": [
    {
      "id": "scan_outgoing_payment",
      "name": "Check a payment before sending it",
      "description": "Call before the agent settles an outgoing x402 payment. Answers 'is this safe to send?' \u2014 catches paying an address that came from injected content the agent just read, replayed nonces, overpayment vs the quote, secrets/PII in payment metadata, fake/lookalike USDC contracts, address poisoning, and reported counterparties. Returns allow/flag/block.",
      "tags": [
        "security",
        "payments",
        "x402",
        "firewall",
        "fraud-detection",
        "prompt-injection",
        "scam-prevention",
        "wallet-security",
        "agent-safety"
      ],
      "examples": [
        "Before I pay this, is it safe?",
        "Check this $0.05 USDC payment to 0xabc\u2026 for fraud before I settle it",
        "Should I pay this address? It came from a webpage I just read."
      ]
    },
    {
      "id": "scan_incoming_payment",
      "name": "Check a 402 offer before paying it",
      "description": "Call before the agent pays a 402 offer / payment request it received. Answers 'is this offer safe to pay?' \u2014 checks the resource URL for spoofing (IP hosts, punycode, shorteners, credential demands), price sanity, replay, and counterparty reputation. Returns allow/flag/block.",
      "tags": [
        "security",
        "payments",
        "x402",
        "firewall",
        "fraud-detection",
        "phishing",
        "scam-prevention"
      ],
      "examples": [
        "Is this 402 quote from api.example.com safe to pay?",
        "This site is asking me to pay \u2014 is it legit?"
      ]
    },
    {
      "id": "counterparty_reputation",
      "name": "Check or report a counterparty address",
      "description": "Look up whether a counterparty address has been reported (scam, non-delivery, prompt injection, overcharge, impersonation, replay abuse), and file your own report for free after a bad experience.",
      "tags": [
        "reputation",
        "payments",
        "x402",
        "fraud-detection",
        "scam-database",
        "blocklist"
      ],
      "examples": [
        "Has anyone reported 0xdef\u2026 for non-delivery?",
        "Is this address known to be a scam?",
        "Report 0xbad\u2026 \u2014 I paid and got nothing."
      ]
    }
  ],
  "payments": {
    "protocol": "x402",
    "network": "eip155:8453",
    "pricing": {
      "POST /v1/scan/outgoing": "$0.01 (less on a plan \u2014 see /v1/plans)",
      "POST /v1/scan/incoming": "$0.01 (less on a plan \u2014 see /v1/plans)",
      "GET /v1/reputation/{address}": "$0.01",
      "POST /v1/reputation/report": "free",
      "GET /v1/plans": "free",
      "POST /v1/plans/subscribe": "x402-paid at the chosen plan's price"
    },
    "freeTier": "first 100 calls per API key",
    "plansCatalog": "https://tollwarden.com/v1/plans",
    "manifest": "https://tollwarden.com/.well-known/x402"
  }
}