Connect stagenth · 网页数据 and your agent gets 4 tools, among them crawl, extract, scrape_url. It answers at https://stagenth.com/mcp/web/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Web scraping to clean Markdown with JS rendering, multi-page crawl, structured extract, sitemaps.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
crawl | 从入口 URL 广度优先抓取多页，每页转干净 Markdown（按实际抓取页数计费，每页 1 credit）。 纯抓取 + 格式转换，不生成任何 AI 内容；逐页 SSRF 校验，单页失败不中断。 Inputs: start_url, max_pages, max_depth, same_domain |
extract | 结构化抽取网页要素（表格/链接/图片/标题大纲/元数据/自定义 CSS 选择器），返回 JSON。 与 scrape_url 的区别：不返回整页正文，只返回指定结构——表格转成 headers+rows 的 JSON 可直接计算；配自定义选择器可精准取价格/标题等字段。 Inputs: url, targets, selectors |
scrape_url | 抓取一个公开网页，返回干净的 Markdown（供 AI 阅读/总结/提取）。 只抓公开网页，禁止内网/保留地址；不生成任何内容，只做抓取与格式转换。 静态抓取拿不到内容的 JS 动态页可加 render=true 走真浏览器渲染。 Inputs: url, only_main_content, formats, render |
site_map | 发现站点 URL 清单：优先 robots.txt / sitemap.xml，无站点地图时退化为入口页链接发现。 配合 scrape_url / crawl 使用：先 site_map 挑准页面，再精准抓取，省 credit。 Inputs: url, max_urls |
Every block below points at https://stagenth.com/mcp/web/. Pick your client and copy.
claude mcp add --transport http stagenth https://stagenth.com/mcp/web/
{
"mcpServers": {
"stagenth": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://stagenth.com/mcp/web/"]
}
}
}{
"mcpServers": {
"stagenth": {
"url": "https://stagenth.com/mcp/web/"
}
}
}{
"servers": {
"stagenth": {
"type": "http",
"url": "https://stagenth.com/mcp/web/"
}
}
}{
"context_servers": {
"stagenth": {
"url": "https://stagenth.com/mcp/web/"
}
}
}{
"mcpServers": {
"stagenth": {
"serverUrl": "https://stagenth.com/mcp/web/"
}
}
}{
"mcpServers": {
"stagenth": {
"url": "https://stagenth.com/mcp/web/"
}
}
}name: stagenth · 网页数据
version: 0.0.1
schema: v1
mcpServers:
- name: stagenth · 网页数据
type: streamable-http
url: https://stagenth.com/mcp/web/{
"mcpServers": {
"stagenth": {
"httpUrl": "https://stagenth.com/mcp/web/"
}
}
}{
"mcpServers": {
"stagenth": {
"type": "http",
"url": "https://stagenth.com/mcp/web/"
}
}
}{
"mcpServers": {
"stagenth": {
"url": "https://stagenth.com/mcp/web/"
}
}
}goose://extension?url=https%3A%2F%2Fstagenth.com%2Fmcp%2Fweb%2F&type=streamable_http&id=stagenth&name=stagenth%20%C2%B7%20%E7%BD%91%E9%A1%B5%E6%95%B0%E6%8D%AE
It answered our last check on 18 October 2026 in 961 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by stagenth.com and served from stagenth.com, the vendor's own domain: https://stagenth.com/mcp/web/.
4, as returned by the server's own tools/list on 31 August 2026: crawl, extract, scrape_url, site_map.
It answered our last check on 18 October 2026 in 961 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://stagenth.com/mcp/web/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.stagenth. Endpoint host: stagenth.com. ARD identifier: urn:air:com.stagenth:mcp:web.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.