Agent Safety Index MCP Server

by fizzl13 Your server? Claim it

answering

Agent Safety Index is answering right now. Last checked 6 min ago. It exposes 4 tools. Last commit 9 Nov 2026.

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

Uptime history 10 hours of history

10 hours agonow

100.0%

Uptime 24h

34 of 34 checks

Tools

read from the server

379 ms

Response time

average over 24h

Stars

last commit 9 Nov 2026

Nothing serious here today

Today is the operative word: we check Agent Safety Index every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-safety-index --transport http https://exam.fizzl.eu/mcp

Settings → Connectors → Add custom connector, then paste this address

https://exam.fizzl.eu/mcp

~/.codex/config.toml

[mcp_servers.agent-safety-index]
url = "https://exam.fizzl.eu/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "agent-safety-index": {
      "url": "https://exam.fizzl.eu/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agent-safety-index": {
      "type": "http",
      "url": "https://exam.fizzl.eu/mcp"
    }
  }
}

Available tools 4

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent

agent_safety_check

Look 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, honest tasks done, money lost, whether its admission is current, and links to the signed result and a replay. Free.

agent_safety_demo

Start 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. Demos are not stored. Free.

agent_safety_exam_howto

How 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 message the operator wallet signs for the free exam. Free.

agent_safety_index

Every 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.

Endpoints

URL	Transport	State	Latency	Checked
https://exam.fizzl.eu/mcp	streamable-http	answering	359 ms	6 min ago

Alternatives to Agent Safety Index

same job, measured the same way

Agent Discovery Index

by sadri-dridi

Where AI agents discover products, and how to be listed there with measured results.

31 tools answering

Crypto Market Data

by zaffy18

Live crypto market data and Hyperliquid wallet reports for AI agents, paid per call with x402.

157 installs/wk 15 tools answering

XDC AI

by 0xbeny

Wallet and payments for AI agents: auto-pay x402 APIs in USDC on XDC, within on-chain limits.

answering

Wizeb AI-Native Index

by wizeb

AI-Native Index scoring, PDF report, Wizeb Q&A, and an Enhanced report agents buy over x402.

10 tools answering

Tabula MCP

by tabulacredit

Credit for AI agents: pay x402 sellers from a credit line, repay with one signature and no ETH

local only

Overtone News MCP

by ckbrennan

Real-time news with tone analysis, brand safety, and narrative shift signals for AI agents.

121 installs/wk local only

x402 Trinity

by devmster

Give an agent a wallet. Pays for x402 resources within hard limits. Base + USDC, gasless.

129 installs/wk local only

Rein

by bugiiiii11

Spend limits for AI agents that pay with x402: every paywall is policy-checked before a cent moves.

88 installs/wk local only

Agent Safety Index — questions

Answers built from our own checks of this server.

What can Agent Safety Index do?

It exposes 4 tools, read directly from the server on our last check. Among them: agent_safety_check, agent_safety_demo, agent_safety_exam_howto, agent_safety_index. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Agent Safety Index working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 34 of 34 checks got a reply (100.0%), average response time 379 ms. The bar chart above shows every period we have measured.

How do I connect Agent Safety Index?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Agent Safety Index need an API key?

No. Agent Safety Index completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Agent Safety Index?

It answers our handshake in 379 ms on average, which is faster than 34% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Agent Safety Index open source?

The code is open source: it is published under the MIT licence, written in JavaScript, 0 stars on GitHub and 1 open issue. The licence covers the code in the repository, not the hosted service at exam.fizzl.eu, which runs on its operator's own terms.