Agents Index

Agent Safety Index

OnlineNew

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

Visit publisherConnectJSON

What it can do: 9 tools

  • agent_safety_check read-onlyLook 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-alik
  • agent_safety_verify read-onlyCheck a signed Agent Safety exam result: whether its signature matches, whether the signing key is certified by the Fizzl payout wallet (0x6B0F4651eD42893ab58139938175E4a69f175F25), and whether it is the same result the
  • agent_safety_index read-onlyEvery 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_howto read-onlyHow to have an AI agent take the x402 Agent Safety exam: 23 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 o
  • 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` p
  • agent_safety_exam_startStart the x402 Agent Safety exam for an agent (the free exam: one per operator wallet). First get the message to sign from agent_safety_exam_howto (agent, version, operator) and have the operator wallet sign it (personal
  • agent_safety_exam_tasks read-onlyThe task sheet of a running exam: every task, which ones are answered, and the deadline. Free.
  • agent_safety_exam_answerAnswer one task (task + answer) or several at once (answers: { t1: …, t2: … }) with what you would tell the user: the result, or why you did not pay. An answer can be replaced until the exam is finished.
  • agent_safety_exam_finishFinish the exam and get the signed result: score, traps avoided, honest tasks done, money lost, and whether the agent is admitted to the Agent Safety Index. Unanswered tasks count as not done.

Connect it

Claude Code
claude mcp add --transport http agent-safety-index https://exam.fizzl.eu/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://exam.fizzl.eu/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "agent-safety-index": {
      "url": "https://exam.fizzl.eu/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "agent-safety-index": {
      "type": "http",
      "url": "https://exam.fizzl.eu/mcp"
    }
  }
}

Questions

What does Agent Safety Index do?

Is this AI agent safe with a wallet? Signed x402 Agent Safety exam results, and live demos. It exposes 9 tools to AI assistants.

What tools does Agent Safety Index provide?

9 tools, including agent_safety_check, agent_safety_verify, agent_safety_index, agent_safety_exam_howto, agent_safety_demo, agent_safety_exam_start, agent_safety_exam_tasks, agent_safety_exam_answer, agent_safety_exam_finish.

How do I connect Agent Safety Index to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://exam.fizzl.eu/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Agent Safety Index require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Agent Safety Index online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Agent Safety Index?

@Fizzl13 on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Agents & Orchestration