Bastion Helix Agent Lens

com.bastionhelix由 bastionhelix.com 發布官方發布者v1.0.0更新於 Oct 29, 2026

Web pages for AI agents: may-I-use checks, prompt-injection flags, Markdown, JSON, screenshots

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取瀏覽器自動化資料與分析

概覽

AI 產生的概覽

遠端 MCP 伺服器,讓助理先確認網頁是否可用,再以 Markdown 讀取、擷取結構化資料、比對變更、列出表單並截圖。

可以做什麼
  • 檢查某個網址的使用規則與所需引擎,並檢視網站的 llms.txt、網站地圖、訂閱來源和 AI 爬蟲規則
  • 把網頁正文讀成帶絕對連結的乾淨 Markdown,依序嘗試一般抓取、Kitesurf、Chromium
  • 擷取頁面已發布的結構化資訊:JSON-LD/schema.org、價格、meta 與 Open Graph 標籤、訂閱來源和 HTML 表格
  • 回傳上次的指紋,只取有變動的章節
  • 列出頁面上的表單、欄位、按鈕和連結,並附上可用的 CSS 選擇器
  • 以 1280x800 或整頁擷取 PNG 截圖
適用情境
適合需要穩定讀取或持續監控網頁、同時遵守 robots.txt 與 Content Signals、並避免在機器人驗證或登入頁白費力氣的助理。delta 適合反覆檢查的頁面,actions 適合建立表單填寫或點擊自動化。
執行需求
遠端 streamable HTTP 端點 lens.bastionhelix.com,不需本機安裝。免費工具(preflight、site、credits)不需金鑰。付費工具需要 Authorization 標頭中的 Bearer API 金鑰,或透過 Base 上的 USDC x402 付款。需要能連線該服務及目標網站。
安裝前請注意
付費工具會花錢:actions 每次成功呼叫 US$0.004,screenshot 每次成功呼叫 US$0.008,以預付額度或 x402 加密貨幣支付。Authorization 標頭帶有金鑰。服務會代你抓取第三方網址,目標網站會看到其請求。site 工具依 IP 限流。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Bastion Helix Agent Lens,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/com.bastionhelix%2Fagent-lens/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": {
    "bastion-helix-agent-lens": {
      "type": "http",
      "url": "https://lens.bastionhelix.com/mcp"
    }
  }
}

工具

8

preflight

Check a page before using it

Free. Before an agent spends money or time on a URL: is it allowed (robots.txt for this service and, if you pass user_agent, for your own bot; Content Signals such as ai-input and ai-train; meta robots), does a bot check or sign-in stand in the way, and which engine each task needs — plain fetch, Kitesurf (Cloudflare's lightweight agent browser) or Chromium. Rate-limited per IP.

輸入參數url必填user_agent

read

Read a page as clean Markdown

Returns the main content of a web page as clean Markdown with absolute links. Tries the cheapest way that works: plain fetch, then Kitesurf, then Chromium, and reports which one worked. Refuses (and charges nothing) when the site's robots.txt or Content Signals say no, or when a bot check answers instead of the page. Charged only on success. Price: US$0.004 per successful call (API key credits or x402).

輸入參數url必填enginemax_charsuser_agent

actions

List what can be clicked or filled

Returns the forms (with every field, its label and whether it is required), buttons and links on a page, each with a CSS selector an automation tool can use. Uses the rendered page when the HTML alone has none. Charged only on success. Price: US$0.004 per successful call (API key credits or x402).

輸入參數url必填engineuser_agent

extract

Get the facts a page publishes, as JSON

No AI model involved: returns the structured data the page already publishes — JSON-LD / schema.org objects (products, articles, events, organisations, breadcrumbs), prices and offers, meta and Open Graph tags, canonical URL, language versions, licence, RSS/Atom/JSON feeds, and HTML data tables as columns + rows. Exact values instead of guesses from text. Charged only on success. Price: US$0.002 per successful call (API key credits or x402).

輸入參數url必填engineuser_agent

delta

What changed since last time

For pages an agent checks again and again. The first call returns the page as sections plus a fingerprint; send that fingerprint back as "previous" next time and get only the sections that changed (and the headings of removed ones), or changed:false. Uses HTTP ETag/Last-Modified when the site supports them. Nothing is stored on our side: the fingerprint lives with the agent. Saves tokens on every re-check. Charged only on success. Price: US$0.001 per successful call (API key credits or x402).

輸入參數url必填engineprevioususer_agent

site

Site card for agents

Free. Everything an agent should know about a website before using it: its llms.txt (and llms-full.txt), sitemap (page count and first URLs), feeds, language versions, Content Signals, and which known AI crawlers and agents its robots.txt allows. Rate-limited per IP.

輸入參數url必填user_agent

screenshot

Screenshot a page

PNG screenshot of a page at 1280×800 (or the full page). engine "auto" uses Kitesurf unless the page needs video or WebGL, then Chromium. Charged only on success. Price: US$0.008 per successful call (API key credits or x402).

輸入參數url必填enginefull_pageuser_agent

credits

Credits left on your API key

Free. Credits remaining on the API key sent in the Authorization header (1 credit = US$0.001).

無需輸入參數。

版本歷史

1
  1. v1.0.0最新Oct 29, 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。

其他 Bastionhelix 整合