What configuration is required?
You must set the `WEBSCRAPING_AI_API_KEY` environment variable. Optional settings include concurrency limit, proxy type, JavaScript rendering, and content sandboxing.
WebScraping.AI MCP Server
@webscraping-ai
基本信息
关于 WebScraping.AI MCP Server
A Model Context Protocol (MCP) server implementation that integrates with WebScraping.AI for web data extraction capabilities.
WebScraping.AI MCP Server 配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"WebScraping.AI": {
"command": "npx",
"args": [
"-y",
"webscraping-ai-mcp"
],
"env": {
"WEBSCRAPING_AI_API_KEY": "test-api-key"
}
}
}
}WebScraping.AI MCP Server 工具
7概览
What is WebScraping.AI MCP Server?
A Model Context Protocol (MCP) server that integrates with WebScraping.AI to provide web data extraction capabilities for LLM platforms like Claude. It enables AI agents to scrape, extract, and answer questions from web page content.
How to use WebScraping.AI MCP Server?
Run with npx -y webscraping-ai-mcp after setting the required WEBSCRAPING_AI_API_KEY environment variable. Configure in Cursor (.cursor/mcp.json) or Claude Desktop (claude_desktop_config.json) with optional settings like WEBSCRAPING_AI_CONCURRENCY_LIMIT (default 5) and WEBSCRAPING_AI_ENABLE_CONTENT_SANDBOXING. Tools are invoked via MCP tool calls.
Key features of WebScraping.AI MCP Server
- Question answering about web page content
- Structured data extraction from web pages
- HTML content retrieval with JavaScript rendering
- Plain text extraction from web pages
- CSS selector-based content extraction
- Multiple proxy types (datacenter, residential, stealth)
- Content sandboxing to prevent prompt injection
Use cases of WebScraping.AI MCP Server
- Answer specific questions from any public web page
- Extract product details (title, price, description) from e‑commerce sites
- Retrieve full HTML or visible text for content analysis
- Scrape multiple page sections using CSS selectors
- Monitor account usage and remaining API quota
常见问题
What is content sandboxing?
When enabled (`WEBSCRAPING_AI_ENABLE_CONTENT_SANDBOXING=true`), scraped content is wrapped with security boundaries and a warning not to execute commands from that section, helping protect LLMs against indirect prompt injection.
What proxy types are available?
Three proxy types: `datacenter`, `residential`, and `stealth`. Residential is the default. Stealth is recommended for heavily protected sites but costs more.
How does the server handle errors?
It provides automatic retries for transient errors, rate limit handling with backoff, and returns detailed error messages (e.g., HTTP 429).
What transport does the server use?
The server connects via STDIO transport, configured as a command in MCP‑enabled platforms. Authentication is done through the API key passed as an environment variable.
其他 分类下的更多 MCP 服务器
Senso MCP for Joomla
sensomediaSenso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea
N
Next Generation Movers: free moving quotes (remote MCP)
Next Generation MoversFree moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
DeepMark
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
26.0K
Lemon.io
lemon-ioRequest dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
评论