X402 Presign Guard runs on your own machine — the client starts it, so there is no endpoint to ping. 610 installs a week from npm. Last commit 24 Oct 2026.
Pre-sign EVM tx/approval safety for AI agents: decode calldata, flag drainers, return GO/HOLD/BLOCK.
Today is the operative word: we check X402 Presign Guard every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add x402-presign-guard -- npx -y x402-presign-guard
{
"mcpServers": {
"x402-presign-guard": {
"command": "npx",
"args": [
"-y",
"x402-presign-guard"
]
}
}
}
[mcp_servers.x402-presign-guard]
command = "npx"
args = ["-y", "x402-presign-guard"]
{
"mcpServers": {
"x402-presign-guard": {
"command": "npx",
"args": [
"-y",
"x402-presign-guard"
]
}
}
}
{
"servers": {
"x402-presign-guard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"x402-presign-guard"
]
}
}
}
Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call
Solana pre-trade safety for agents: rug check, honeypot sell-sim, drainer scan, tx preflight.
Pre-trade safety verdicts for agents: token rug/honeypot, calldata guard, wallet risk — signed x402.
DeFi safety layer for AI agents: wallet safety, token risk, tx decode/simulate. 20 tools.
Read-only crypto safety: token honeypot checks, EIP-712 signature decode, approval scans.
Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
Spend approval gate for AI agents: budget caps, HITL thresholds, signed audit hash.
Pre-sign Solana tx guard for agents: ALLOW/WARN/BLOCK verdict, x402 USDC pay-per-call.
Answers built from our own checks of this server.