FaceabotCapability network for AI agents
‹ Back

Catalog › io.github.Fizzl13/agent-safety-index

Is Agent Safety Index reliable?

Reliable (measured) Yes. Faceabot measured Agent Safety Index 4 times: 100% of checks succeeded, including the last 4 in a row (last check 2026-11-19 02:35 UTC). It also does the job: its real read-only task worked 4 of 4 times.

Last check: 2026-11-19 02:35 UTC · answered in 217 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

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

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.2.0 · publisher website
Connect your agent
{
  "mcpServers": {
    "agent-safety-index": {
      "url": "https://exam.fizzl.eu/mcp"
    }
  }
}
Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.Fizzl13/agent-safety-index"} on https://faceabot.com/api/mcp.
Does it actually do the job?

Does the job (tested) — Faceabot asked agent_safety_index to do a small read-only task 4 time(s): 4 returned a real result, the last 4 in a row. Last result: ok in 433 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.
Other proven tools for the same job

PayStage — x402 payment safety Reliable (measured) · 100%
x402 payment safety: stop your agent paying a drainer before the wallet signs. · https://api.paystage.xyz/mcp

x402-payment-safety Reliable (measured) · 98%
Authorize x402 payments before signing with request-bound, signed safety decisions. · https://agent-guild-5d5r.onrender.com/mcp/payment-safety/

AI Agent Safety Foundational Certificate Reliable (measured) · 100%
AI Agent Safety Foundational Certificate: a wallet-signed 40-task exam. First 3 attempts free. · https://certify.sarnai.dev/mcp

Picked from Faceabot's live measurements. Or let Faceabot choose: GET https://faceabot.com/resolve?need=…
Faceabot measurements
WhenAnswersReal taskLatency
2026-11-19 02:35 UTC✅ ok✅ done217 ms
2026-11-15 14:20 UTC✅ ok✅ done782 ms
2026-11-12 04:35 UTC✅ ok✅ done340 ms
2026-11-08 17:00 UTC✅ ok✅ done870 ms
Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

More from the same publisher

AgentFuel Flaky · 60% over 5 checks Does the job (tested) · 3/3

Safety checks for trading bots: Solana and Robinhood Chain rug-checks, launch feed, safe_buy.

MCP endpoint : https://api.agentfuel.eu/mcp · website · measurements and details
Fizzl Buy Reliable (measured) · 100% over 16 checks

Say what your agent needs: Fizzl buys the right paid x402 API, checks the answer. Free pick.

MCP endpoint : https://buy.fizzl.eu/mcp · website · measurements and details
Ichimoku Signal Flaky · 89% over 9 checks Fails real tasks · 0/8

Free Ichimoku trend; paid signals, levels, scan, setups and Telegram signal alerts via x402.

MCP endpoint : https://ichimoku-signal.fizzl.eu/mcp · website · measurements and details
PayPal, guarded Not measured yet

PayPal's Agent Toolkit with limits on refunds and the owner's Approve/Deny above them.

Package npm : fizzl-paypal-guard-mcp · website · measurements and details
PlainText Wallet Approval Checker Flaky · 62% over 13 checks

Explains wallet approvals and signature requests in plain language: SAFE, CAUTION or RISK.

MCP endpoint : https://plaintext.fizzl.eu/mcp · website · measurements and details

Find tools similar to Agent Safety Index →

Publisher of Agent Safety Index?

Show your measured reliability on your README or website:

Faceabot reliability badge for Agent Safety Index

[![Measured by Faceabot](https://faceabot.com/badge/io.github.Fizzl13/agent-safety-index.svg)](https://faceabot.com/tools/io.github.Fizzl13/agent-safety-index)
Data in JSON: /api/catalog?id=io.github.Fizzl13/agent-safety-index · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms