找到适合你的 MCP Server，快速完成接入

Browserbase MCP Server

Allow LLMs to control a browser with Browserbase and Stagehand

ScrapeGraph MCP

@smithery/cli

ScapeGraph MCP Server

Oxylabs MCP Server

Official Oxylabs MCP integration

Steel MCP Server

@smithery/cli

MCP Server for interacting with a Steel web browser

WebScraping.AI MCP

@modelcontextprotocol/inspector

A Model Context Protocol (MCP) server implementation that integrates with WebScraping.AI for web data extraction capabilities.

ScrAPI MCP

ScrAPI MCP Server 是一个强大的网页抓取解决方案，提供从任何网站轻松提取数据的功能，支持处理反爬虫机制和地理位置限制。

Olostep MCP Server

Search Google, scrape webpage and retrieve content in markdown.

PlayMCP Browser Automation Server

playwright

一个基于Playwright的全面浏览器自动化服务器，提供38种工具用于网页抓取、测试和自动化。

UseScraper MCP Server

@smithery/cli

MCP server for the useScraper API. This is a server that scrapes a URL to text or markdown

Puppeteer-Extra MCP Server

MCP server for browser automation using puppeteer-extra and puppeteer-extra-plugin-stealth

Firecrawl MCP Server

firecrawl-mcp

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

Fetcher MCP 4f2a5b38

fetcher-mcp

MCP server for fetch web page content using Playwright headless browser.

Douyin MCP Server

一款从短视频分享链接下载无水印视频并自动提取语音文案的工具，支持WebUI、MCP集成和命令行操作。

hyperbrowser MCP

hyperbrowser-mcp

Hyperbrowser的模型上下文协议(MCP)服务器，提供网页抓取、结构化数据提取和网页爬取工具，并支持通用浏览器代理如OpenAI CUA和Anthropic Claude。

Selenium MCP

@smithery/cli

MCP Selenium Server是一个为AI代理提供的Selenium WebDriver浏览器自动化服务，支持多种浏览器操作和交互。

Playwright MCP

@smithery/cli

MCP server for browser automation using Playwright

Puppeteer MCP Server

puppeteer-mcp-server

一个基于Puppeteer的浏览器自动化服务器，提供网页导航、截图、表单填写等功能，支持连接现有Chrome窗口。

Scrapeless MCP Server

scrapeless-mcp-server

Scrapeless MCP Server lets LLMs and AI tools like ChatGPT and Cursor access real-time web data via Google services, browser automation, and scraping—no blocks, just seamless context.

Crw MCP

crw-mcp

Web scraping, crawling, and data extraction for AI agents. 5 built-in tools: scrape (clean markdown from any URL), crawl (follow links across entire sites), map (discover all URLs on a domain), extract (structured JSON via schema), and search (web search with optional page scraping). 833ms average latency, single binary, 6 MB RAM. Self-host free or use managed cloud at fastcrw.com with 500 free credits. Firecrawl-compatible API. Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible client.\\r\\n\\r\\n

Chotu Robo Server

Chotu Robo Server是一个基于Arduino和ESP32的机器人控制服务器，通过MCP框架与AI集成，实现远程控制硬件组件如LED、电机、传感器等。适用于物联网、自动化和教育场景。