com.stagenth/web

MCPcommunitydegraded
v1.0.0com.stagenthUnknownUpdated 3mo ago

Web scraping to clean Markdown with JS rendering, multi-page crawl, structured extract, sitemaps.

Endpoint healthdegraded
checked 13 days ago · last reachable 33 days ago
60% of the last 5 checks reached this endpoint
Works in
ClaudeCursorCopilotChatGPTGemini

Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
3mo agoLast update
Package
Authorcom.stagenth
LicenseUnknown
Version1.0.0
Sourcemcp-registry
Trust Status
B
60/100Good
Hosted endpoint only: this assessment covers who publishes it and whether it answers, not the code behind it. No CVE, dependency or source analysis applies, so nothing here is a clean bill for that code.
✓Listed in Forge index+10/10
—Publisher identity verified+0/30
→ Publisher: this listing has no repository on file, so `forge publish` cannot verify ownership automatically. Use "Claim this listing" above — Forge reviews these by hand.
—Domain verification+0/10
→ Not currently available for this listing type — the domain-verification check only runs for npm-backed packages today, so this row cannot be earned here yet regardless of what's hosted at the domain.
✓Prompt-injection scan · clean+30/30
✓Obfuscation / exfil scan · clean+20/20
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
DependenciesNot audited
Tool surface4 tools · none privileged
Security scan✓ Cleanvlive · 1mo agoHow well does this scan work?
EvalsNone
IndexedJul 7, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

4 tools · none privileged
Observed live from the vendor's endpoint1mo ago

Read from a real MCP initialize → tools/list handshake against the declared endpoint. No tool was ever invoked — tools/list is the read-only introspection call the protocol defines for this. It reflects what the server advertised at that moment; a hosted endpoint is not pinned to any version and can change without notice.

  • https://stagenth.com/mcp/web/4 tools · 677ms
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。

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。

ParameterTypeDescription
url*string要抓取的网页 URL(http/https,仅限公开网页)
only_main_contentboolean只提取正文主体,去掉导航/广告/页脚
formats—输出格式子集:markdown / html / text,默认 markdown
renderboolean经境内托管浏览器真渲染 JS 后再抽取(适合动态页),默认关闭
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。

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。

ParameterTypeDescription
start_url*string入口页 URL(http/https,仅限公开网页)
max_pagesinteger最多抓取页数(1-20)
max_depthinteger链接跟踪深度(0-3,0=只抓入口页)
same_domainboolean只跟踪同域名链接
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。

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。

ParameterTypeDescription
url*string要抽取的网页 URL(http/https,仅限公开网页)
targets—抽取目标子集:metadata / headings / links / images / tables,默认 metadata+headings+links+tables
selectors—可选 CSS 选择器映射 {名称: 选择器},每个选择器返回匹配元素的文本列表
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。

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。

ParameterTypeDescription
url*string站点入口 URL(用于确定站点与域名)
max_urlsinteger最多返回 URL 数(1-1000)

4 of 4 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

Web scraping to clean Markdown with JS rendering, multi-page crawl, structured extract, sitemaps.

Keywords
mcp
Alternatives
Comparing tool surfaces…

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.