How do I connect an AI agent to AI Catalog by Crescendo Lab?

Use the MCP streamable HTTP endpoint https://catalog.cresclab.com/api/mcp/.

Catalog › com.cresclab.catalog/ai-catalog

Is AI Catalog by Crescendo Lab reliable?

Reliable (measured) Yes. Faceabot measured AI Catalog by Crescendo Lab 40 times: 100% of checks succeeded, including the last 40 in a row (last check 2026-10-19 11:05 UTC). It also does the job: its real read-only task worked 40 of 40 times.

Last check: 2026-10-19 11:05 UTC · answered in 5724 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

Check if a product feed is ready for AI shopping (ChatGPT, Gemini, AI Mode): score, gaps, fixes.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "ai-catalog": {
      "url": "https://catalog.cresclab.com/api/mcp/"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.cresclab.catalog/ai-catalog"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked get_feed_fix_guide to do a small read-only task 40 time(s): 40 returned a real result, the last 40 in a row. Last result: ok in 2734 ms.

Sample input: {}. 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 11:05 UTC	✅ ok	✅ done	5724 ms
2026-10-18 18:30 UTC	✅ ok	✅ done	4363 ms
2026-10-18 06:15 UTC	✅ ok	✅ done	8749 ms
2026-10-17 22:25 UTC	✅ ok	✅ done	4111 ms
2026-10-17 14:05 UTC	✅ ok	✅ done	7524 ms
2026-10-17 06:10 UTC	✅ ok	✅ done	5985 ms
2026-10-16 22:25 UTC	✅ ok	✅ done	4202 ms
2026-10-16 15:15 UTC	✅ ok	✅ done	4912 ms
2026-10-16 08:15 UTC	✅ ok	✅ done	4956 ms
2026-10-16 01:20 UTC	✅ ok	✅ done	8296 ms
2026-10-15 18:25 UTC	✅ ok	✅ done	8631 ms
2026-10-15 11:41 UTC	✅ ok	✅ done	4814 ms
2026-10-15 05:05 UTC	✅ ok	✅ done	3893 ms
2026-10-14 22:40 UTC	✅ ok	✅ done	5666 ms
2026-10-14 16:10 UTC	✅ ok	✅ done	6075 ms
2026-10-14 09:40 UTC	✅ ok	✅ done	3754 ms
2026-10-14 03:01 UTC	✅ ok	✅ done	7029 ms
2026-10-13 20:41 UTC	✅ ok	✅ done	7219 ms
2026-10-13 14:31 UTC	✅ ok	✅ done	7460 ms
2026-10-13 08:25 UTC	✅ ok	✅ done	6980 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 AI Catalog by Crescendo Lab?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.cresclab.catalog/ai-catalog.svg)](https://faceabot.com/tools/com.cresclab.catalog/ai-catalog)

Data in JSON: /api/catalog?id=com.cresclab.catalog/ai-catalog · 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