Stringer CleanExtract

Convert public HTML or a public URL into token-dense Markdown through one remote MCP tool.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
100%
命名质量
80%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~394token 数(工具定义)
~1.2 KB典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.31%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "cleanextract": {
      "url": "https://extract.getstringer.app/mcp"
    }
  }
}

远程端点

https://extract.getstringer.app/mcpstreamable-http

它能做什么

工具清单

工具(2)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢clean_extract(url_or_html, max_output_bytes, sections)

Extract a full page or selected sections from a public URL or raw HTML. A call is charged only when it returns usable content; the first 3 usable extraction calls are free, total, then USD 0.05. Use the free clean_extract_outline first. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used. Every success reports extraction_quality and extraction_content_ratio_band.

输入模式

{
  "type": "object",
  "properties": {
    "url_or_html": {
      "type": "string",
      "minLength": 1,
      "description": "A public HTTP(S) URL or a raw HTML string to convert into Markdown."
    },
    "max_output_bytes": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1048576,
      "description": "Optional maximum UTF-8 byte length of the returned Markdown."
    },
    "sections": {
      "type": "array",
      "minItems": 1,
      "maxItems": 50,
      "items": {
        "type": "string",
        "pattern": "^s[1-9][0-9]*$"
      },
      "description": "Optional ids from clean_extract_outline. Return only these sections in document order."
    }
  },
  "required": [
    "url_or_html"
  ],
  "additionalProperties": false
}
🟢clean_extract_outline(url_or_html)

Free outline with section ids, headings, byte sizes, and a fingerprint, without page body text or payment. A later clean_extract call can select sections and is charged only when it returns usable content. Uncharged failures name upstream_timeout, upstream_http_error, bot_challenge, js_shell, empty_extraction, or sections_not_found. Recoverable structured data names fallback_used.

输入模式

{
  "type": "object",
  "properties": {
    "url_or_html": {
      "type": "string",
      "minLength": 1,
      "description": "A public HTTP(S) URL or a raw HTML string to convert into Markdown."
    }
  },
  "required": [
    "url_or_html"
  ],
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本2 个工具
已验证未记录版本1 个工具