浏览器与抓取 MCP 服务器

Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported.

MCP server for web search operations

Playwright Tools for MCP

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

AI-powered web scraping library that creates scraping pipelines using natural language.- [ScrapeGraphAI](https://scrapegraphai.com)

AI-powered browser automation — navigate, click, fill forms, and extract data from any website.

Stealthy browser automation, testing, and web-scraping via CDP Mode.

MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.

Automate your local Chrome browser

An MCP server using Playwright for browser automation and webscrapping

MCP server for JavaScript analysis, security auditing, browser automation and hooks

Leverage Notte Web AI agents & cloud browser sessions for scalable browser automation & scraping workflows

browser-use packaged as an MCP server with SSE transport. includes a dockerfile to run chromium in docker + a vnc server.

Open-source MCP-native browser agent with human takeover via noVNC, reusable auth profiles, and approval/audit rails. Playwright +…

[Hyperbrowser](https://www.hyperbrowser.ai/) is the next-generation platform empowering AI agents and enabling effortless, scalable…

The AI-powered toolkit that grows your YouTube channel on autopilot

Fetch YouTube subtitles and transcripts for AI analysis

Local browser automation for MCP clients powered by DrissionPage.

An MCP server that enables free web searching using Google search results, with no API keys required.

Control and debug Firefox: navigate, fill forms, inspect network and console, profile.

SHAFT browser automation, capture, and offline deterministic failure diagnosis

An MCP Server Integration with Apple Shortcuts

An MCP server paired with a browser extension that enables LLM clients to control the user's browser (Firefox).

Public Spotify metadata, lyrics and podcasts for LLM agents. No API key, read-only.

An MCP server for browser automation using Playwright

AI browser automation. Write async Python to navigate, click, type, and extract data.

An MCP server for interacting with Apple Reminders on macOS

Native Safari browser automation for AI agents — 98 tools, zero Chrome overhead.

A MCP server that supports searching for Bilibili content. Provides LangChain integration examples and test scripts.

An MCP python server using Playwright for browser automation,more suitable for llm

Connect to Perplexity Comet browser for agentic web browsing, deep research, and real-time task monitoring.

AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.

AI-powered web scraping and data extraction capabilities through ScrapeGraph API

Self-hosted MCP server for stealth browser automation with human-like OS-level input.

Rust MCP stealth scraper: anti-bot search/scrape with CDP fallback + HITL non-robot.

Playwright MCP-compatible browser automation bridge for CloakBrowser Chromium.

MCP server for automated web accessibility scanning with Playwright and Axe-core.

An MCP Server that enables AI assistants to interact with your local browsers.

Drive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent.

MCP server + Chrome extension for AI browser control with real sessions.

Drive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too.

Stealth browser automation over raw CDP, driving real unmodified Chrome with no Playwright or Puppeteer in the stack. Returns numbered…

MCP server for parallel browser automation across multiple providers.

Lightweight browser automation MCP server in Rust with zero dependencies.

A Model Context Protocol (MCP) integration that provides Claude Desktop with autonomous browser automation capabilities.

MCP server with WebdriverIO for browser and mobile app automation (iOS/Android via Appium)

Structured web intelligence for AI agents. 5x fewer tokens than Playwright/Firecrawl, 84.7% accuracy

Fetch content from login-protected web pages (Notion, Google Docs, Jira, Confluence, etc.) by opening a real browser for authentication…

A `minimal` server/client MCP implementation using Azure OpenAI and Playwright.

Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.

One MCP for devs incl Brave,Google,Tavily,Context7,AWS,Excalidraw,DB,GitHub,DevTools,Playwright

Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.

Web scraping, crawling, and search API. Extract content in Markdown/JSON, batch process 10k URLs, and get AI-powered answers with citations.

Fetch transcripts, subtitles, chapters, metadata and frames from YouTube and 10+ video platforms

MCP server for Zen Browser automation via WebDriver BiDi

Playwright for the Windows desktop, from Bun — drive native GUIs via UI Automation + MCP.

Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.

Token-efficient browser automation for LLM agents: semantic page snapshots and stable element IDs instead of raw DOM or screenshots,…

iOS Safari debugging via ios-webkit-debug-proxy — MCP server with full WebKit Inspector Protocol support (DOM, CSS, Network, Storage,…

Chrome-free MCP web access for agents with low-token page maps and browser escalation hints.