agent_threat_intel
Query the OWASP Agentic Top 10 threat catalog (ASI01-ASI10). Returns threats, detection hints, mitigations, and mapped security-cannibal rule IDs. CC BY-SA 4.0 (OWASP derivative).
What is agent_threat_intel?
agent_threat_intel is a paid MCP tool in the Security category on agenttoll.dev. It costs $0.03 per call, settled in USDC on Base via the x402 payment protocol. No API keys, no accounts — your agent discovers it via /.well-known/agent.json, calls it, pays the $0.03 fee, and receives structured JSON.
Input parameters
{
"category": "optional: e.g. 'prompt injection', 'supply chain'",
"id": "optional: e.g. ASI04",
"severity": "optional: critical, high, medium"
}
Example usage
{
"category": "supply chain"
}
HTTP endpoint
POST to this path with JSON body. Server returns 402 with x402 payment requirements.
/paid/security/threat-intel
How to call agent_threat_intel
Connect any MCP-compatible client (Claude Desktop, Cursor, custom agent) to the agenttoll.dev MCP endpoint:
https://agenttoll.dev/mcp
Or call the HTTP endpoint directly with an x402-capable fetch client.
Pricing & payment
FAQ
How much does agent_threat_intel cost?
$0.03 per call in USDC on Base. No subscriptions or minimums.
Do I need an API key?
No. Payment is handled by the x402 protocol. Your agent wallet sends USDC on Base, the server verifies the transfer, and returns the data.
Which AI models work with agent_threat_intel?
Any model that supports MCP — Claude, GPT-4, Gemini, or local models via an MCP client. The tool returns structured JSON that any model can parse.
How do I verify my payment?
After settlement, check /receipt/<tx> for on-chain verification via Basescan. Every payment is a real USDC transfer to 0x62a0D3d9…
