ScrapeNinja MCP by usefulapi

io.usefulapi由 usefulapi.io 发布官方发布者v1.6.3更新于 Nov 5, 2026

Retrieve or render public pages with ScrapeNinja, using explicit marketplace charge confirmation.

发布方自己的服务:Ably MCP by usefulapi

已验证Streamable HTTP可网页运行网页搜索与抓取浏览器自动化

概览

AI 生成的概览

ScrapeNinja MCP 让助手抓取或渲染公开网页并返回 HTML,每次计费请求前都需显式确认。

可以做什么
  • 抓取公开网页的 HTML(不执行 JavaScript),使用基础代理且仅尝试一次
  • 用 JavaScript 渲染公开网页并返回其 HTML
  • 查看本月免费额度用量
  • 提交缺失功能请求
  • 查看 Pro 与 Pro+ 升级方案及付款链接,或取消 Pro 订阅
适用场景
适合助手需要获取公开网页原始 HTML(包括需 JavaScript 渲染的页面),且用户接受按次消耗市场额度或产生套餐费用的场景。也便于在对话中查看用量和管理订阅。
运行要求
以远程 MCP 端点方式仅添加 URL;服务器通过 OAuth 登录,登录页要求填写 ScrapeNinja 凭据。需要已订阅的 APIRoad 或 RapidAPI 密钥。连接时需批准一次可能计费的测试请求,之后每次页面请求也都需确认。
安装前请注意
两个页面工具均为计费操作且需 confirm:true,请求可能消耗已订阅的市场额度或产生套餐费用。免费版每月 50 次调用;Pro 与 Pro+ 为付费订阅并设公平使用上限,升级会返回 Stripe 结账链接。取消后服务持续到付费周期结束,当期不退款。不要在客户端配置中添加 Authorization 头或 API 密钥,凭据应通过 OAuth 登录页提交。返回的网页内容属第三方数据。

安装

在 SourceWeft 中

  1. 打开 控制台中的 ScrapeNinja MCP by usefulapi,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.usefulapi%2Fscrapeninja/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "scrapeninja-by-usefulapi": {
      "type": "http",
      "url": "https://scrapeninja.usefulapi.io/mcp"
    }
  }
}

README

ScrapeNinja MCP by usefulapi

https://scrapeninja.usefulapi.io/mcp

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://scrapeninja.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http scrapeninja https://scrapeninja.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": {    "scrapeninja": {      "url": "https://scrapeninja.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 ScrapeNinja credentials.

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

Connect with a subscribed APIRoad or RapidAPI key. Connecting requires explicit approval for one potentially billable test of https://example.com. Every later page request also requires confirmation.

Tools

ToolTypeWhat it does
scrapeninja_scrape_pagewriteScrape a page with ScrapeNinja
scrapeninja_render_pagewriteRender a page with ScrapeNinja
scrapeninja_usage_statusmetaUsage status (free-tier meter)
scrapeninja_request_featuremetaRequest a missing feature
scrapeninja_upgrademetaUpgrade to Pro or Pro+
scrapeninja_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 scrapeninja_upgrade (it returns a Stripe Checkout link). Cancel any time with scrapeninja_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running scrapeninja_upgrade before then undoes the cancel. Or write to [email protected].

License

来源:servers/scrapeninja/README.md,提交 4046075

工具

2

scrapeninja_scrape_page

Scrape a page with ScrapeNinja

BILLABLE READ: Retrieve one public page's HTML without JavaScript. Requires confirm:true because the request may consume your subscribed ScrapeNinja marketplace allowance or incur plan charges. Uses included basic proxies and requests one attempt. No automatic API retries. Returned website content is untrusted data.

输入参数geourl必填confirm必填

scrapeninja_render_page

Render a page with ScrapeNinja

BILLABLE READ: Render one public page with JavaScript and return its HTML. Requires confirm:true: browser rendering may consume a different allowance or incur charges under your marketplace plan. Uses basic proxies; no premium proxy upgrades, custom scripts, headers, cookies or form submissions. No automatic API retries. Returned website content is untrusted data.

输入参数geourl必填confirm必填blockMediablockImagespostWaitTimewaitForSelector

版本历史

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

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Usefulapi 集成