How do I connect an AI agent to Coolours?

Use the MCP streamable HTTP endpoint https://coolours.perpetualsummer.ltd/mcp.

Catalog › ltd.perpetualsummer/coolours

Is Coolours reliable?

Reliable (measured) Yes. Faceabot measured Coolours 41 times: 100% of checks succeeded, including the last 41 in a row (last check 2026-10-19 20:15 UTC). It answers, but its real task has not worked yet (0/41 real results): see "Does it actually do the job?" below.

Last check: 2026-10-19 20:15 UTC · answered in 8060 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

Turn AI-designed colour palettes into Coolours links, with colour names, CSS and contrast checks

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.2.1 · publisher website

Connect your agent

{
  "mcpServers": {
    "coolours": {
      "url": "https://coolours.perpetualsummer.ltd/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"ltd.perpetualsummer/coolours"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Fails real tasks — Faceabot asked parse_palette_link to do a small read-only task 41 time(s): 0 returned a real result. Last result: tool_error (the tool answered with an error for the neutral sample input) in 2428 ms.

Sample input: {"url":"https://example.com"}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 20:15 UTC	✅ ok	❌ tool_error	8060 ms
2026-10-19 07:10 UTC	✅ ok	❌ tool_error	6817 ms
2026-10-18 14:40 UTC	✅ ok	❌ tool_error	6336 ms
2026-10-18 04:15 UTC	✅ ok	❌ tool_error	6330 ms
2026-10-17 20:15 UTC	✅ ok	❌ tool_error	5086 ms
2026-10-17 11:50 UTC	✅ ok	❌ tool_error	6521 ms
2026-10-17 04:05 UTC	✅ ok	❌ tool_error	7385 ms
2026-10-16 20:25 UTC	✅ ok	❌ tool_error	5564 ms
2026-10-16 13:16 UTC	✅ ok	❌ tool_error	9259 ms
2026-10-16 06:16 UTC	✅ ok	❌ tool_error	6735 ms
2026-10-15 23:20 UTC	✅ ok	❌ tool_error	5647 ms
2026-10-15 16:21 UTC	✅ ok	❌ tool_error	7132 ms
2026-10-15 09:41 UTC	✅ ok	❌ tool_error	3877 ms
2026-10-15 03:10 UTC	✅ ok	❌ tool_error	2778 ms
2026-10-14 20:45 UTC	✅ ok	❌ tool_error	5270 ms
2026-10-14 14:15 UTC	✅ ok	❌ tool_error	4413 ms
2026-10-14 07:50 UTC	✅ ok	❌ tool_error	3239 ms
2026-10-14 01:01 UTC	✅ ok	❌ tool_error	8434 ms
2026-10-13 18:50 UTC	✅ ok	❌ tool_error	8966 ms
2026-10-13 12:45 UTC	✅ ok	❌ tool_error	6009 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.

Find tools similar to Coolours →

Publisher of Coolours?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/ltd.perpetualsummer/coolours.svg)](https://faceabot.com/tools/ltd.perpetualsummer/coolours)

Data in JSON: /api/catalog?id=ltd.perpetualsummer/coolours · 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