{
  "status": "success",
  "token": "0xYourTargetToken...",
  "recommendation": "REJECT",
  "confidence": 0.99,
  "reasons": [
    "Honeypot detected: sell simulation failed",
    "Deployer address linked to multiple previous rugpulls"
  ]
}⚙️ How It Works (M2M Architecture)
Agent Discovers Token via mempool or DEX router event.

Agent Calls AgentRisk MCP Tool (check_token_risk).

Instant x402 Micropayment ($0.15 USDC instantly settled on Base — no cumbersome API keys, subscriptions, or credit cards; pure machine-to-machine payment).

Binary Decision: The agent receives ALLOW, CAUTION, or REJECT. If it's not ALLOW, the bot aborts the trade instantly.

🚀 Quick Integration
Option 1: MCP Server (For Claude, Cursor & Custom Agents)
Add AgentRisk to your MCP config:
{
  "mcpServers": {
    "agentrisk": {
      "command": "python",
      "args": ["-m", "agentrisk_m2m.server"]
    }
  }
}
Option 2: Direct Python SDK / API Call
from agentrisk import AgentRiskClient

client = AgentRiskClient(endpoint="[https://agentrisk.dev](https://agentrisk.dev)", network="base")

# Pre-trade check before executing swap
verdict = client.check_token(
    token_address="0xTargetTokenAddress...",
    amount_usdc=50
)

if verdict.recommendation == "ALLOW":
    execute_swap()
else:
    print(f"Trade aborted. Risk detected: {verdict.reasons}")
💰 Economy
Model: Pay-per-scan via the x402 protocol.

Cost: 0.15 USDC per comprehensive deep simulation.

ROI: Losing $100 on a single honeypot costs more than 600 security scans. Protect your liquidity.

Built for autonomous systems that trust math, not hype.