Agent Safety Index

io.github.Fizzl13/agent-safety-index · v1.0.0 · agents-and-memory

Agent Safety Index is healthy: it completed an MCP handshake in 1226 ms and exposes 4 tools.

Is this AI agent safe with a wallet? Signed x402 Agent Safety exam results, and live demos.

Endpoint: https://exam.fizzl.eu/mcp (streamable-http)

Repository · Website · JSON · Add to my inventory

Facts

Users (last 30 days)0
HandshakeHealthy
Auth neededNone
Tool count4
Latency1226 ms
Last checked (UTC)2026-11-08T22:10:18.089Z

Health history

Checked (UTC)StatusLatencyError
2026-11-08T22:10:18.089ZHealthy1226

Tools (4)

agent_safety_checkLook up an AI agent in the Agent Safety Index: did it pass the x402 Agent Safety exam (paying honest x402 sellers, refusing cheating ones: overcharges, sanctioned payees, injected instructions, pay-again loops, look-alike payout addresses)? Returns its latest signed result: score, traps avoided, hon
agent_safety_indexEvery agent's latest result in the Agent Safety Index (admitted ones first): score, traps avoided, honest tasks done, money lost, admitted or not, valid until. Free.
agent_safety_exam_howtoHow to have an AI agent take the x402 Agent Safety exam: 19 tasks at simulated x402 sellers on Base Sepolia (test money, nothing settled), 30 minutes. The first exam per operator wallet is free; every next one is $0.10 over x402. Given the agent and the operator wallet, also returns the exact messag
agent_safety_demoStart a demo: a scripted agent takes the x402 Agent Safety exam slowly enough to follow, and you get a link to watch it live (every request, every 402, every x402 Doctor check, every signed payment). `follow-preflight` pays only when x402 Doctor's preflight says go; `always-pay` pays every 402. Demo