How do I connect an AI agent to Website Feedback Tool?

Use the MCP streamable HTTP endpoint https://dfozgzaflbudvthtlhvn.supabase.co/functions/v1/mcp.

Faceabot

‹ Back

Catalog › tools.websitefeedback/website-feedback-tool

Is Website Feedback Tool reliable?

Flaky Partly. Faceabot measured Website Feedback Tool 21 times and only 95% of checks succeeded. Plan a fallback.

Last check: 2026-10-17 07:15 UTC · answered in 8000 ms · remote (no install)

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

What it does

Read visual design reviews from live web pages: comments, CSS selectors, styles, console errors.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.1.2 · publisher website

Connect your agent

{
  "mcpServers": {
    "website-feedback-tool": {
      "url": "https://dfozgzaflbudvthtlhvn.supabase.co/functions/v1/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"tools.websitefeedback/website-feedback-tool"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-17 07:15 UTC	❌ timeout		8000 ms
2026-10-16 23:30 UTC	✅ ok	—	6493 ms
2026-10-16 16:20 UTC	✅ ok	—	8223 ms
2026-10-16 09:20 UTC	✅ ok	—	9936 ms
2026-10-16 02:31 UTC	✅ ok	—	8835 ms
2026-10-15 19:35 UTC	✅ ok	—	7162 ms
2026-10-15 12:50 UTC	✅ ok	—	4044 ms
2026-10-15 06:15 UTC	✅ ok	—	4496 ms
2026-10-14 23:45 UTC	✅ ok	—	5811 ms
2026-10-14 17:25 UTC	✅ ok	—	6624 ms
2026-10-14 10:55 UTC	✅ ok	—	4598 ms
2026-10-14 04:26 UTC	✅ ok	—	9803 ms
2026-10-13 21:46 UTC	✅ ok	—	9537 ms
2026-10-13 15:40 UTC	✅ ok	—	7699 ms
2026-10-13 09:31 UTC	✅ ok	—	10885 ms
2026-10-13 03:25 UTC	✅ ok	—	10336 ms
2026-10-12 21:20 UTC	✅ ok	—	8521 ms
2026-10-12 15:15 UTC	✅ ok	—	9912 ms
2026-10-12 09:10 UTC	✅ ok	—	9525 ms
2026-10-12 03:05 UTC	✅ ok	—	10402 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.

Publisher of Website Feedback Tool?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/tools.websitefeedback/website-feedback-tool.svg)](https://faceabot.com/tools/tools.websitefeedback/website-feedback-tool)

Data in JSON: /api/catalog?id=tools.websitefeedback/website-feedback-tool · 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