OpenWeb Ninja + Agent Safe: Google AI Mode for agents, inside a budget

OpenWeb Ninja serves real-time web data APIs, like Google AI Mode answers, to agents over x402, paid per call in USDC on Base. Agent Safe adds the guardrail people need before leaving an agent running: payments go only to OpenWeb Ninja's address, never above your per-call cap, never past the budget, whatever the agent was told.

Tested live on Base mainnet (2026-10-08): an agent paid OpenWeb Ninja 0.005 USDC for GET /google-ai-mode/ai-mode?prompt=What%20is%20Base%20L2%3F and got a Google AI Mode answer to "What is Base L2?". Transaction. The same 402 checked against a different payee was refused with zero signatures.

1. Add OpenWeb Ninja as a merchant

import { createAgentPay, MerchantRegistry } from "@deepfirstsearch/agent-pay";

const registry = new MerchantRegistry([{
  origin: "https://x402.openwebninja.com",
  payTo: "0x3e7c9cA818f713F19e126E3B7B37B47dC1411570", // OpenWeb Ninja's Base address, as in its 402
  network: "eip155:8453",
  maxPerTx: 10_000n, // never more than 0.01 USDC per call
  pricePin: 5_000n, // 0.005 USDC, the published price
  label: "OpenWeb Ninja",
}]);

2. Pay per call

const pay = createAgentPay({
  registry,
  policy: { allowedNetworks: ["eip155:8453"], periodBudget: { amount: 1_000_000n, periodMs: 86_400_000 } },
  payer: () => yourWallet, // any viem account: local key, Turnkey, Privy, CDP, KMS
  session: { readsUntrustedInput: true, accessesSensitiveData: false, canPay: true },
});
const plan = pay.commitPlan([{ origin: "https://x402.openwebninja.com", maxSpend: 100_000n }], 60 * 60_000);

const res = await pay.fetch("https://x402.openwebninja.com/google-ai-mode/ai-mode?prompt=What%20is%20Base%20L2%3F", { method: "GET" }, { plan });
console.log(res.status, res.payment?.settlement.transaction);

A 402 that asks for a different payee, a higher price or a different network is refused before anything is signed. Requires @deepfirstsearch/agent-pay 0.5.3 or later.

3. Or through MCP (Claude, Cursor, OpenClaw)

Add to the merchants of your agent-pay-mcp config, then ask the agent to use https://x402.openwebninja.com/google-ai-mode/ai-mode?prompt=What%20is%20Base%20L2%3F:

{ "origin": "https://x402.openwebninja.com", "label": "OpenWeb Ninja", "payTo": "0x3e7c9cA818f713F19e126E3B7B37B47dC1411570",
  "price": "0.005", "maxPerTx": "0.01", "maxSpend": "1.00" }

If OpenWeb Ninja changes its price or address

The pins are deliberate. The 402 is written by the server, and a 402 that suddenly names another address or a higher price is exactly what a redirected or hijacked payment looks like. So when OpenWeb Ninja reprices or rotates its wallet, Agent Safe refuses and nothing is signed:

a higher price gives price_changed (action ask_owner), or over_cap if it is also above your per-call cap;
a different address gives payee_mismatch (action report).

Confirm the change through OpenWeb Ninja's own channels (its site, docs or announcement), then update pricePin or payTo in the registry, or price or payTo in the MCP config. To absorb small price changes without a prompt, allow a tolerance instead of removing the pin: toleranceBps in the registry (1000 = up to 10% over the pin) or tolerancePct in the MCP config.

Agent Safe is an independent open-source project (MIT), live on Base mainnet as an unaudited beta. Not affiliated with OpenWeb Ninja.