xfix

ai.xfix由 xfix.ai 發布官方發布者v1.1.1更新於 Nov 7, 2026

Check if AI assistants and shopping agents can read a website or online store

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取資料與分析商業與電商

概覽

AI 產生的概覽

檢查 AI 助理與購物代理能否讀取某個公開網站或線上商店,並給出 AI 可見性與購物就緒度評分。

可以做什麼
  • 依九種爬蟲讀取 robots.txt,判斷哪些可抓取指定頁面並指出攔截規則
  • 檢查頁面可讀性,以及商品頁中的價格、庫存與結構化資料欄位
  • 執行含評分的頁面可見性檢查,稍後再取得結果或進度
  • 查詢商店在 AI 購物就緒度指數中的分數,並檢查商店的 AI 就緒情況
  • 對照 Google Ad Grants 網站政策的可見條款檢查非營利組織網站
適用情境
適合在需要釐清 AI 助理或購物代理為何讀不到某個網站、robots.txt 是否阻擋特定爬蟲,或想了解商店、非營利網站的就緒度與政策檢查分數時使用。
執行需求
遠端 streamable HTTP 端點;未宣告套件、環境變數或請求標頭。工具會透過網路抓取公開頁面,因此目標網址必須可公開存取。
安裝前請注意
工具會抓取使用者指定的公開頁面與網域,這些網址會傳送給 xfix 服務。結果僅涵蓋 HTML 與 robots.txt 中可見的內容,不含 CDN 或防火牆規則;可見性檢查耗時較長,需要輪詢取得結果。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 xfix,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.xfix%2Fxfix/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "xfix": {
      "type": "http",
      "url": "https://mcp.xfix.ai/mcp"
    }
  }
}

工具

8

check_store_ai_readiness

Check store AI shopping readiness

Checks whether AI assistants and shopping agents can read an online store. Fetches the public store pages the user names, without running JavaScript. Returns the store's AI Shopping Readiness Index score if the store is in the Index, which AI crawlers its robots.txt allows, and whether one product page shows price, stock and product structured data in its HTML. Use when the user asks if AI can find, read or shop their store. Does not test checkout or log in. Use when the user gives a store or domain.

輸入參數store_url必填product_url

check_ai_crawler_access

Check AI crawler access

Reads a site's robots.txt the way 9 crawlers do (Googlebot, Bingbot, Applebot, OAI-SearchBot, ChatGPT-User, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User) and returns which may fetch the given page and the rule that blocks each one. Does not see CDN or firewall rules. Use when the user asks which bots or crawlers can access, crawl or read a site, or asks about robots.txt.

輸入參數url必填

check_page_readability

Check page text without JavaScript

Fetches the public page at the given URL without running JavaScript and reports whether its main text is present in the HTML. Checks one page only. Use when the user asks whether a page's content can be read without JavaScript.

輸入參數url必填

check_product_page

Check product page price and schema

Fetches one public product page without running JavaScript and reports whether the price and stock are in the HTML and which of six product structured data fields are present: price, availability, brand, identifier (gtin or sku), shipping details and aggregate rating. Use when the user gives a product page URL.

輸入參數product_url必填

check_page_visibility

Run xfix search visibility check

Runs the xfix search check on one public page: fetches it without running JavaScript, checks robots.txt for 9 crawlers, measures mobile speed and reviews text, headings and title. Returns a score out of 100, a grade, coverage, any failed gates and the 5 biggest point losses with fixes. Takes about a minute; if not finished within about 25 seconds, returns a check_id to fetch the result later.

輸入參數url必填

get_page_visibility_result

Get xfix search result

Returns the result of an xfix search check started earlier, or its progress if it is still running.

輸入參數check_id必填

lookup_index_score

Look up AI Shopping Readiness Index score

Looks up a store domain in the xfix AI Shopping Readiness Index and returns its published score and the fields shown on the public Index page, or says the store is not in the Index. Does not fetch the store.

輸入參數domain必填

check_ad_grants_website

Check nonprofit website for Google Ad Grants

Checks a nonprofit's public website against the visible parts of Google's Ad Grants website policy: the domain serving the site itself, HTTPS, a findable mission, a physical address and registration number, real content on the key pages, working links and donate buttons, a mobile viewport and no ad-serving code. Reads the homepage, About, Programs, Contact and the donate destination without running JavaScript or submitting anything. Returns each policy rule as pass, fail or not checked, with what was seen and the fix. Does not access any Google account; passing does not guarantee approval. Use when the user asks about Google Ad Grants eligibility or their nonprofit website's readiness for it.

輸入參數domain必填

版本歷史

2
  1. v1.1.1最新Nov 7, 2026
  2. v1.1.0Oct 19, 2026

評分

已滿足適用檢查項的 83%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分

    請宣告包含 README 的 GitHub 儲存庫,或在 OAuth 受保護資源後設資料中提供 resource_documentation。

  • 授權條款不適用

    託管服務按其提供方的條款使用,因此這裡不要求授權條款。此檢查項不計入百分比。