AI Catalog by Crescendo Lab
Check if a product feed is ready for AI shopping (ChatGPT, Gemini, AI Mode): score, gaps, fixes.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"ai-catalog": {
"url": "https://catalog.cresclab.com/api/mcp/"
}
}
}远程端点
https://catalog.cresclab.com/api/mcp/streamable-http它能做什么
工具清单
工具（3）
🟢scan_product_feed(feed_url, locale)
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.
输入模式
{
"type": "object",
"properties": {
"feed_url": {
"type": "string",
"description": "Public URL of the product feed or Shopify store, e.g. https://example.com/feed.xml or https://shop.example.com"
},
"locale": {
"type": "string",
"enum": [
"en",
"zh-TW"
],
"description": "Language for shopper questions and labels (default en)."
}
},
"required": [
"feed_url"
]
}🟢get_feed_fix_guide(issue_key)
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.
输入模式
{
"type": "object",
"properties": {
"issue_key": {
"type": "string",
"description": "Issue key from scan_product_feed, e.g. no_specs, thin_desc, llm_unanswerable. Omit for all."
}
}
}🟢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.
输入模式
{
"type": "object",
"properties": {}
}社区
证据