Browser automation using Puppeteer, supporting local and remote browser connections.
Browser Automation
Browser automation servers expose actions such as navigation, screenshots and page interaction to an MCP client. Check which browser they control, whether they reuse an existing session, and what access they need.

Playwright browser automation: interact with web pages through structured accessibility snapshots.
Headless browser for AI and web automation with a built-in MCP server.
Browser automation, testing and bot-detection bypass using SeleniumBase CDP Mode with Chromium, including click-based CAPTCHA solving.
Firecrawl web scraping: search, scrape, crawl, map and extract structured data, with live browser interaction and website change monitoring.
Automate your local Chrome browser.
Browser automation and web scraping using Playwright.
Browser agent with human takeover via noVNC, reusable auth profiles, approval and audit controls, and isolated Docker sessions.
Browser automation with browser-use, including a Dockerfile to run Chromium in Docker with a VNC server.
Automate YouTube operations, also available as a CLI.
Fetch YouTube subtitles and transcripts for AI analysis.
Firefox automation via WebDriver BiDi: snapshot-based interactions, network monitoring, console capture and screenshots for testing and scraping.
Web search using Google search results.
Integration with Apple Shortcuts.
Control the user's Firefox browser via a companion extension.
Browser automation using Playwright.
Interact with Apple Reminders on macOS.
Native Safari browser automation without a Chrome dependency.
Search Bilibili content, with LangChain integration examples.
Browser automation using Playwright, tailored for LLMs.
Connect to the Perplexity Comet browser for agentic browsing, deep research and real-time task monitoring.
Playwright MCP-compatible browser automation using CloakBrowser Chromium.
Web scraper that returns clean Markdown, distributed as a single binary.
Control your real, logged-in Chrome browser via an extension, with multiple concurrent color-coded sessions.
Browse the web with filesystem commands (ls, cd, grep, click) by mapping Chrome's accessibility tree to a virtual filesystem via an extension.
Control the user's real Chrome browser via an extension, reusing existing sessions, logins and cookies.
Interact with your local browsers.
Stealth automation of unmodified Chrome over raw CDP, using accessibility-tree element refs; can attach to a running Chrome to reuse logged-in sessions.
Autonomous browser automation.
Browser and mobile app automation with WebdriverIO: control browsers and automate native Android and iOS apps via WebDriver and Appium.
Lightweight browser automation with zero dependencies.
Chromium-free agent browser with built-in V8: tiered fetching, multi-engine search, screenshots, persistent login sessions and CDP access.
Compress web page HTML into compact structured maps that preserve actionable elements, so agents can read and interact with pages using fewer tokens.
Fetch content from login-protected pages such as Notion, Google Docs, Jira and Confluence via a real browser login with persistent session caching.
Minimal MCP server and client implementation using Azure OpenAI and Playwright.
Get transcripts and metadata for summarization and content analysis.
Web scraping, crawling and search API: extract content as Markdown or JSON, batch-process URLs and get answers with citations.
Zen Browser automation via WebDriver BiDi: navigation, form filling, screenshots and JavaScript evaluation.
Self-hosted web scraping: scrape, extract, crawl, map, search, academic papers, research and monitoring, with a tiered fallback including Cloudflare bypass.
Local-first web reading escalating from HTTP to a real browser when blocked: clean Markdown, site crawls, search, row extraction and local CAPTCHA handling.
iOS Safari debugging via ios-webkit-debug-proxy with WebKit Inspector Protocol support: DOM, CSS, network, storage, debugger and more.
Chrome automation over raw CDP with multiple tabs, cached accessibility-tree refs, server-side multi-step flow execution and a Python scripting API.
Compile browser automation into deterministic plans that run in your logged-in Chrome without runtime LLM calls, detecting drift when sites change.
Token-efficient browser automation: semantic page snapshots and stable element IDs instead of raw DOM or screenshots, driving Chrome over CDP.
Code-aware browser testing that reads routes, forms and existing tests, runs Playwright scenarios, and keeps regression history and screenshot reports.
Lightweight native browser that runs JavaScript, follows links, fills forms, manages cookies and returns low-token BlockMaps, without Chrome.
Autonomous, goal-driven LLM web crawler with stealth browsing, distributed as a single binary.
Fetch trending videos from Bilibili.