81trust / 100
Guard
by tool-call-guard in Onchain & crypto
x402 APIPassing, checked 3 h ago
Ask whether a tool call should run automatically, need human confirmation, or be denied, given the user's request - returns allow/ask/deny with a probability. Advisory only: like any LLM-based judge it is sensitive to prompt injection in the request or tool call, so the calling agent must keep the final decision, not delegate it outright. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /guard/sample.
POST https://x402.agentindex.world/guard
Last 30 days
All checks passedSome failedAll failedNot checked
- Uptime
- 100%
- Response time
- 46 ms typical, 46 ms slowest 5%
- Last check
- 3 h ago
- Next check
- any minute now
How to call it
# See the payment challenge (nothing is charged)
curl -i -X POST "https://x402.agentindex.world/guard" \
-H "content-type: application/json" \
-d '{"tool_call":{"arguments":{"path":"/","recursive":true},"name":"delete_files"},"user_request":"Clean up my project folder, it's gotten messy."}'import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
const client = new x402Client().register(
"eip155:8453",
new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? Preflight it first for $0.03:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fx402.agentindex.world%2Fguard
const res = await pay("https://x402.agentindex.world/guard", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({"tool_call":{"arguments":{"path":"/","recursive":true},"name":"delete_files"},"user_request":"Clean up my project folder, it's gotten messy."}),
});
console.log(await res.json());Example input
{
"tool_call": {
"arguments": {
"path": "/",
"recursive": true
},
"name": "delete_files"
},
"user_request": "Clean up my project folder, it's gotten messy."
}Example output
{
"confidence": 0.89,
"decision": "deny",
"probabilities": {
"allow": 0,
"ask": 0.08,
"deny": 0.92
},
"probability": 0.92,
"x402_receipt": {
"latency_ms": 420,
"model_served": "jev",
"price_paid_usdc": 0,
"upstream": "guardrail"
}
}Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 3 h ago | Passed | 402 | 46 ms | $0.001 |