scrapegraph-mcp

概述

ScrapeGraph MCP 服务器是 Model Context Protocol 的生产级实现，连接语言模型与 ScrapeGraph AI API。它使 AI 助手能够执行复杂的网页抓取任务，从网站提取结构化数据，爬取多个页面，并根据自然语言提示生成模式。服务器提供本地和远程部署选项，并包含 Claude Desktop 和 Cursor 的完整集成指南。

试试问 AI

装完之后，这里有 3 个你可以让 AI 做的事：

• scrape

  Scrape content from web pages with various output formats

  试试:Convert https://example.com to markdown试试:Extract all product prices from this e-commerce page试试:Get me all the links from this website
• extract

  Extract specific information from a website using AI

  试试:Extract all product prices from this e-commerce page试试:Get me all the contact information from this business website试试:Extract the main headlines from this news article
• search

  Search the web with customizable parameters

  试试:Search for recent AI research papers and summarize them试试:Research the latest developments in quantum computing试试:Find the top 5 restaurants in Paris with the highest ratings
• crawl_start

  Start an async multi-page crawl

  试试:Start crawling all product pages on this e-commerce site试试:Begin crawling this documentation site to extract all API endpoints试试:Initiate a crawl of all blog posts on this technology site
• crawl_get_status

  Check the status of a running crawl job

  试试:Check the status of my website crawl试试:How is the crawling of the e-commerce site going?试试:Is my data extraction job complete?
• crawl_stop

  Stop a running crawl job

  试试:Stop the current website crawl试试:Pause the crawling process试试:Abort the data extraction job
• crawl_resume

  Resume a paused crawl job

  试试:Resume the website crawl from where it left off试试:Continue the paused data extraction job试试:Restart the crawling process
• schema

  Generate or augment a JSON Schema from a prompt

  试试:Generate a schema for product information extraction试试:Create a JSON schema for capturing restaurant reviews试试:Augment this schema with additional fields for news articles
• credits

  Check remaining API credits

  试试:How many credits do I have left?试试:Check my account credits试试:Show my remaining API credits
• history

  View historical usage of API services

  试试:Show me my scraping history试试:Get my recent API usage试试:List all the extractions I've done this month
• monitor_create

  Create a scheduled monitoring job

  试试:Create a monitor to track price changes on this e-commerce site试试:Set up a monitor to check for updates on this blog试试:Create a scheduled job to extract stock prices every day
• monitor_list

  List all monitoring jobs

  试试:Show me all my monitoring jobs试试:List my scheduled scraping tasks试试:What monitors do I have active?

可对比工具

安装

npx -y @smithery/cli install @ScrapeGraphAI/scrapegraph-mcp --client claude

{
    "mcpServers": {
        "@ScrapeGraphAI-scrapegraph-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "@smithery/cli@latest",
                "run",
                "@ScrapeGraphAI/scrapegraph-mcp",
                "--config",
                "\"{\\\"scrapegraphApiKey\\\":\\\"YOUR-SGAI-API-KEY\\\"}\""
            ]
        }
    }
}

{
  "mcpServers": {
    "scrapegraph-mcp": {
      "command": "npx",
      "args": [
        "mcp-remote@0.1.25",
        "https://scrapegraph-mcp.onrender.com/mcp",
        "--header",
        "X-API-Key:YOUR_API_KEY"
      ]
    }
  }
}

scrapegraph-mcp 对比