Skip to main content
Glama
Skrape MCP Server

Skrape MCP Server

Official
by skrapeai

Skrape MCP 服务器

铁匠徽章使用skrape.ai将任何网页转换为干净的、可用于 LLM 的 Markdown 格式。非常适合将网页内容输入 LLM。

此 MCP 服务器提供一个简单的界面,可使用 skrape.ai API 将网页转换为结构化、简洁的 Markdown 格式。它旨在与 Claude Desktop、其他 LLM 以及兼容 MCP 的应用程序无缝协作。

为什么使用 Skrape 进行 LLM 集成?

  • 干净、结构化的输出:生成格式良好的 Markdown,非常适合 LLM 使用

  • 降噪:自动删除广告、导航菜单和其他不相关内容

  • 一致的格式:确保网页内容无论来源如何,都具有统一的结构

  • JavaScript 支持:通过在转换之前渲染 JavaScript 来处理动态内容

  • LLM 优化:非常适合将 Web 内容输入到 Claude、GPT 和其他 LLM 模型等 LLM 中

Related MCP server: Scraper MCP

特征

工具

  • get_markdown - 将任何网页转换为 LLM 适用的 Markdown

    • 接受任何输入 URL 和可选参数

    • 返回针对 LLM 使用进行了优化的干净、结构化的 Markdown

    • 支持 JavaScript 渲染动态内容

    • 用于高级集成的可选 JSON 响应格式

安装

通过 Smithery 安装

要通过Smithery自动为 Claude Desktop 安装 Skrape MCP 服务器:

npx -y @smithery/cli install @skrapeai/skrape-mcp --client claude

手动安装

  1. 从skrape.ai获取您的 API 密钥

  2. 安装依赖项:

npm install
  1. 构建服务器:

npm run build
  1. 将服务器配置添加到 Claude Desktop:

在 MacOS 上:

nano ~/Library/Application\ Support/Claude/claude_desktop_config.json

在 Windows 上:

notepad %APPDATA%/Claude/claude_desktop_config.json

添加此配置(用您的值替换路径和 API 密钥):

{
  "mcpServers": {
    "skrape": {
      "command": "node",
      "args": ["path/to/skrape-mcp/build/index.js"],
      "env": {
        "SKRAPE_API_KEY": "your-key-here"
      },
    }
  }
}

与法学硕士 (LLM) 合作

以下是如何将服务器与 Claude 或其他 LLM 模型一起使用:

  1. 首先,确保你的 LLM 应用程序中的服务器配置正确

  2. 然后,您可以要求 ALLMI 获取并处理任何网页:

Convert this webpage to markdown: https://example.com

Claude will use the MCP tool like this:
<use_mcp_tool>
<server_name>skrape</server_name>
<tool_name>get_markdown</tool_name>
<arguments>
{
  "url": "https://example.com",
  "options": {
    "renderJs": true
  }
}
</arguments>
</use_mcp_tool>

生成的 Markdown 将会干净、结构化,并可供 LLM 处理。

高级选项

get_markdown工具接受以下参数:

  • url (必填):要转换的任何网页 URL

  • returnJson (可选):设置为true以获取完整的 JSON 响应,而不仅仅是 markdown

  • options (可选):其他抓取选项

    • renderJs :是否在抓取之前渲染 JavaScript(默认值:true)

包含所有选项的示例:

<use_mcp_tool>
<server_name>skrape</server_name>
<tool_name>get_markdown</tool_name>
<arguments>
{
  "url": "https://example.com",
  "returnJson": true,
  "options": {
    "renderJs": false
  }
}
</arguments>
</use_mcp_tool>

发展

对于使用自动重建的开发:

npm run watch

调试

由于 MCP 服务器通过 stdio 进行通信,调试起来可能比较困难。我们建议使用MCP Inspector :

npm run inspector

检查器将提供一个 URL 来访问浏览器中的调试工具。

Available Tools

1 tool
get_markdownC

Get markdown content from a webpage using skrape.ai

Inputs: url (required), returnJson, options.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or confusion between tools. The tool's purpose is clearly defined as retrieving markdown content from webpages, making it distinct by default.

    Naming Consistency5/5

    A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The name 'get_markdown' follows a clear verb_noun pattern, which would be consistent if more tools were added.

    Tool Count2/5

    A single tool is too few for a server named 'Skrape MCP Server', which suggests a broader scraping or data extraction purpose. This minimal toolset limits functionality and feels incomplete for the implied scope, as it only handles markdown retrieval without other common scraping operations.

    Completeness1/5

    The server is severely incomplete for a scraping domain. It lacks basic operations such as fetching HTML, extracting specific elements, handling different content types, or managing sessions. With only one tool for markdown, agents will face dead ends when trying to perform typical scraping tasks.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.
      10
      1
      225,076 PyPI
      91,952
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      A context-optimized web scraping server that converts HTML to markdown/text and applies CSS selectors server-side, reducing token usage by 70-90% while providing AI tools with clean, filtered web content.
      8
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      A server that extracts clean Markdown from web pages using headless Chrome, reducing token usage by up to 90% for AI tools like Claude.
      ISC
    • A
      license
      Not graded
      quality
      D
      maintenance
      Converts any webpage into clean, LLM-ready Markdown, removing noise and supporting JavaScript rendering.
      MIT