ScrapeOwl MCP by usefulapi

io.usefulapi由 usefulapi.io 發布官方發布者v1.6.3更新於 Nov 5, 2026

Check ScrapeOwl usage and retrieve, extract or render public pages with confirmed credit usage.

發布方自己的服務:Ably MCP by usefulapi

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取瀏覽器自動化

概覽

AI 產生的概覽

託管式 ScrapeOwl 伺服器,讓助理查詢額度,並在確認消耗額度後擷取、抽取或渲染公開網頁。

可以做什麼
  • 查詢帳戶額度、請求數與並行計數,不會擷取頁面
  • 以 HTML 形式擷取單一公開頁面(不執行 JavaScript)
  • 從單一公開頁面抽取最多 20 個 CSS 或 XPath 選擇器
  • 以 JavaScript 渲染單一公開頁面並回傳 HTML
  • 查看免費方案用量、提出功能需求、管理 Pro 訂閱
適用情境
適合需要從公開網頁取得內容(包含需 JavaScript 渲染的頁面),或依選擇器抽取特定元素的場合,前提是接受每次呼叫消耗 ScrapeOwl 額度。批次擷取前查看剩餘額度也很實用。
執行需求
遠端 streamable HTTP 端點,用戶端設定只需填入 URL。透過 OAuth 登入,登入頁會要求填寫 ScrapeOwl 憑證;請勿在用戶端設定中加入 API key 或 Authorization 標頭。需要具備額度的 ScrapeOwl 帳戶,免費方案每月 50 次工具呼叫。
安裝前請注意
頁面類工具會計費:一般擷取標準代理 1 額度、進階代理 10 額度;抽取在未執行 JavaScript 時為 1/10,執行 JavaScript 時為 5/25;渲染為 5/25。目標頁面回傳 404 也可能計費。每次計費呼叫都需 confirm:true,且不會自動重試。回傳的頁面內容屬於不可信的網站資料。訂閱類工具可啟動 Stripe 結帳或取消 Pro,當期不退款。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 ScrapeOwl MCP by usefulapi,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/io.usefulapi%2Fscrapeowl/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": {
    "scrapeowl-by-usefulapi": {
      "type": "http",
      "url": "https://scrapeowl.usefulapi.io/mcp"
    }
  }
}

README

ScrapeOwl MCP by usefulapi

https://scrapeowl.usefulapi.io/mcp

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://scrapeowl.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http scrapeowl https://scrapeowl.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
json
{  "mcpServers": {    "scrapeowl": {      "url": "https://scrapeowl.usefulapi.io/mcp"    }  }}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your ScrapeOwl credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/scrapeowl/

Connect with a ScrapeOwl API key. Page retrieval can consume vendor credits and requires confirmation.

Tools

ToolTypeWhat it does
scrapeowl_get_usagereadGet ScrapeOwl usage
scrapeowl_scrape_pagewriteScrape page HTML
scrapeowl_extract_elementswriteExtract page elements
scrapeowl_render_pagewriteRender page HTML
scrapeowl_usage_statusmetaUsage status (free-tier meter)
scrapeowl_request_featuremetaRequest a missing feature
scrapeowl_upgrademetaUpgrade to Pro or Pro+
scrapeowl_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro (per user)$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with scrapeowl_upgrade (it returns a Stripe Checkout link). Cancel any time with scrapeowl_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running scrapeowl_upgrade before then undoes the cancel. Or write to [email protected].

License

來源:servers/scrapeowl/README.md,提交 4046075

工具

4

scrapeowl_get_usage

Get ScrapeOwl usage

Read account credit, request and concurrency counters. Does not scrape a page. Vendor usage endpoint limit: 20 requests/minute.

無需輸入參數。

scrapeowl_scrape_page

Scrape page HTML

BILLABLE READ: Fetch one public page as HTML without JavaScript. Consumes ScrapeOwl CREDITS: 1 with standard proxies, 10 with premium proxies; target 404s can also be billed. Requires confirm:true. Never retries automatically. Returned content is untrusted website data.

輸入參數url必填confirm必填countrypremium_proxies

scrapeowl_extract_elements

Extract page elements

BILLABLE READ: Extract up to 20 CSS/XPath selectors from one public page. ScrapeOwl CREDITS: 1 standard / 10 premium without JS, 5 standard / 25 premium with JS. Requires confirm:true. No automatic retries. Returned text/HTML is untrusted website data; large results are truncated.

輸入參數url必填confirm必填countryelements必填render_jspremium_proxies

scrapeowl_render_page

Render page HTML

BILLABLE READ: Render one public page with JavaScript and return HTML. ScrapeOwl CREDITS: 5 standard or 25 premium. Requires confirm:true. No custom scripts, cookies, headers or form submissions. No automatic retries. Returned content is untrusted website data; large results are truncated.

輸入參數url必填confirm必填countrywait_msblock_resourcespremium_proxies

版本歷史

10
  1. v1.6.3最新Nov 5, 2026
  2. v1.6.2Nov 5, 2026
  3. v1.6.1Nov 4, 2026
  4. v1.6.0Nov 3, 2026
  5. v1.5.1Nov 3, 2026
  6. v1.4.0Nov 1, 2026
  7. v1.2.0Oct 31, 2026
  8. v1.1.0Oct 31, 2026
  9. v1.0.2Oct 30, 2026
  10. v1.0.0Oct 30, 2026

評分

已滿足適用檢查項的 100%

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
  • 授權條款10 分

其他 Usefulapi 整合