Crescendo LabAI Catalog

MCP server · no API key

Ask your AI agent if a product feed is ready for AI shopping

Connect AI Catalog to Claude, ChatGPT, Cursor or any MCP client. Your agent can scan a product feed, explain each gap, and tell you where product data reaches Gemini, AI Mode and ChatGPT.

Endpointhttps://catalog.cresclab.com/api/mcp/

Connect in one step

Claude.ai / ChatGPT

Settings → Connectors → Add custom connector, paste the endpoint URL. No sign-in needed.

https://catalog.cresclab.com/api/mcp/

Claude Code

claude mcp add --transport http ai-catalog https://catalog.cresclab.com/api/mcp/

Claude Desktop / Cursor / Windsurf

{
  "mcpServers": {
    "ai-catalog": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://catalog.cresclab.com/api/mcp/"]
    }
  }
}

Tools

scan_product_feed

Fetch a public product feed once and score how well AI shopping assistants can understand it (0-100). Returns the biggest gaps (share of products affected), sample shopper questions AI could not answer from the feed, the thinnest products, and a link to fix the gaps. Accepts Google Merchant / Facebook catalog XML, CSV, TSV, or a Shopify store URL. Takes 20-60 seconds. Only summary results are stored.

get_feed_fix_guide

Explain what a gap from scan_product_feed means, why AI shopping assistants need that data, and how to fix it with evidence the merchant already owns. Call with no argument to get the full checklist.

list_ai_shopping_platforms

List the main AI shopping surfaces and how product data reaches each one (e.g. Google Merchant Center for Gemini / AI Mode / Shopping; ChatGPT merchant program). Overview only, not a list of live integrations.

Try asking

Scores do not guarantee AI recommendations. Fixing gaps and publishing to Google Merchant Center happens in the free AI Catalog app — free account, no credit card. Also see llms.txt and the server card.