usescraper-mcp-server

The UseScraper MCP Server is designed to facilitate web scraping by leveraging the UseScraper API. It is implemented in TypeScript and offers a single tool, 'scrape', which allows users to extract content from web pages in various formats. This server is particularly useful for developers and businesses that need to gather data from the web efficiently and reliably. The server supports advanced proxy options to bypass bot detection mechanisms, ensuring that scraping activities are less likely to be blocked. Additionally, it allows for the specification of data extraction objects, providing flexibility in the type of content that can be retrieved. The server can be installed via Smithery or manually, and it integrates seamlessly with platforms like Claude Desktop.

Features

• TypeScript-based implementation for robust performance.
• Single tool 'scrape' for extracting web content.
• Supports multiple content formats: text, html, markdown.
• Advanced proxy option to bypass bot detection.
• Customizable data extraction with 'extract_object'.

MCP Tools

• scrape: Extract content from a webpage with options for format and proxy usage.

Usage with Different Platforms

Claude Desktop

{
  "mcpServers": {
    "usescraper-server": {
      "command": "node",
      "args": ["/path/to/usescraper-server/build/index.js"],
      "env": {
        "USESCRAPER_API_KEY": "your-api-key-here"
      }
    }
  }
}

Smithery

bash
npx -y @smithery/cli install usescraper-server --client claude

Manual Installation

bash
git clone https://github.com/your-repo/usescraper-server.git
cd usescraper-server
npm install
npm run build