Scrapfly MCP Server

Name: Scrapfly MCP Server
Author: scrapfly

@scrapfly

关于 Scrapfly MCP Server

Get real-time web data, automatically handle anti-bot systems, extract structured data, and capture screenshots with your favorite tools, such as Cursor or LangChain.

#web-scraping #data-extraction #anti-bot

基本信息

分类

其他

传输方式

stdio

发布者

scrapfly

提交者

Mariia Platonova

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "scrapfly": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.scrapfly.io/mcp"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Scrapfly MCP Server?

Scrapfly MCP Server is a Model Context Protocol server that provides live web data access with anti-bot handling, structured data extraction, screenshot capture, and secure authentication. It integrates with AI tools like Claude Desktop, Cursor, Cline, Windsurf, LangChain, LlamaIndex, CrewAI, OpenAI function calling, n8n, Make, and Zapier, enabling AI agents to scrape and process web content programmatically.

How to use Scrapfly MCP Server?

Configure the server by adding an entry to your AI tool's MCP configuration (e.g., claude_desktop_config.json). Use npx mcp-remote https://mcp.scrapfly.io/mcp for OAuth2 authentication, or append ?key=YOUR-API-KEY for API key authentication. After restarting the tool, invoke scraping through five available MCP tools: instructions (guidance and required parameters), web_get_page (quick fetch), web_scrape (full‑control scraping), screenshot (visual capture), and info_account (account details).

Key features of Scrapfly MCP Server

Live web data access with automatic JavaScript rendering
Anti‑bot handling and proxy infrastructure
Structured data extraction and clean markdown output
Full‑page or element‑level screenshot capture (PNG)
Secure authentication via OAuth2 or API key
Works with popular AI agents and automation platforms

Use cases of Scrapfly MCP Server

Job aggregation from multiple listing sites
Price monitoring and competitor intelligence
Content research and data aggregation for RAG systems
Real‑estate analysis from public property listings
Automated multi‑step web workflows (e.g., login, fill, navigate)

FAQ from Scrapfly MCP Server

What authentication methods are supported?

OAuth2 (recommended) and API key passed via a URL query parameter (?key=YOUR-API-KEY).

What tools does Scrapfly MCP Server provide?

Five tools: instructions (guidance and required pow value), web_get_page (quick fetch with optimized defaults), web_scrape (full‑control with browser automation), screenshot (visual capture), and info_account (account/project details).

What data formats are available for page content?

Web pages can be returned as clean markdown text (with optional only_content setting) or screenshots in PNG format (full‑page or element‑level).

Do I need a Scrapfly account to use this server?

Yes, for API key authentication you need a Scrapfly API key. OAuth2 also requires a Scrapfly account to authenticate through the MCP endpoint. The info_account tool returns account status and quota details.