sentinel_guard
Check a blockchain transaction's safety before an AI agent signs it. Returns SAFE/UNSAFE verdict, SENTINEL Score, and risk flags.
Instructions
ALWAYS call this tool before an AI agent signs or sends a transaction.
Input: the transaction (to, data, value) and the agent's address. Returns verdict (SAFE/UNSAFE/UNKNOWN), a SENTINEL Score (0-100) + grade (AAA-D), risk flags and a signed receipt. Only sign if verdict is SAFE and score >= 70. $0.005 USDC via x402 (Base).
Args: chain: chain id string (default 'base'). from_addr: the agent's wallet address (the transaction sender). tx: the transaction to evaluate before signing, e.g. {"to": "0x...", "data": "0x...", "value": "0x0"}.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "sentinel_guard"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tx | No | ||
| chain | No | base | |
| from_addr | No |