UseScraper MCP Server

Name: UseScraper MCP Server
Author: MCP-Mirror

@MCP-Mirror

リポジトリ

UseScraper MCP Server について

Mirror of

#web-scraping #typescript #mcp-server

基本情報

カテゴリ

その他

トランスポート

stdio

公開者

MCP-Mirror

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

ツール

Extract content from a webpage

概要

What is UseScraper MCP Server?

It is a TypeScript-based MCP server that provides web scraping capabilities using the UseScraper API. It exposes a single scrape tool to extract content from web pages in formats like text, HTML, or markdown.

How to use UseScraper MCP Server?

Clone the repository, run npm install and npm run build, then configure the server with Claude Desktop by adding its entry to the config JSON file with the command node and the path to the built index.js. Set the USESCRAPER_API_KEY environment variable, then use the scrape tool via the MCP interface with the required url and optional format, advanced_proxy, and extract_object parameters.

Key features of UseScraper MCP Server

Single scrape tool for web page content extraction.
Supports output formats: text, html, markdown (default).
Optional advanced proxy to bypass bot detection.
Option to specify an extract_object for targeted data extraction.
Built with TypeScript for reliability.
Easy integration with Claude Desktop via MCP.

Use cases of UseScraper MCP Server

Extract article content from news websites in markdown format.
Scrape product details from e-commerce pages.
Retrieve raw HTML source of a webpage for analysis.
Gather text content from documentation pages for processing.
Use with AI assistants to fetch real-time web data.

FAQ from UseScraper MCP Server

What does the 'scrape' tool do?

It extracts content from a given URL and returns it in the specified format (text, html, or markdown).

What parameters does the scrape tool accept?

The required parameter is url; optional parameters are format (default markdown), advanced_proxy (default false), and extract_object for defining specific data to extract.

How do I set up the server with Claude Desktop?

Add the server configuration to the Claude Desktop config file (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json; Windows: %APPDATA%/Claude/claude_desktop_config.json) with the command node, args pointing to the built index.js, and the environment variable USESCRAPER_API_KEY.