Playwright、Chrome DevTools、ウェブドライバー。 1,003 件のサーバーを利用の多い順に掲載しています。それぞれ公開元のページが開きます。
AI-powered browser automation with Gemini – fast, cheap Stagehand alternative
Reactive web automation platform — pipelines, templates, and real-time collaboration in a single binary.
MCP server for all VisuallyJs packages
Chrome DevTools for AI assistants: console, network, DOM, source maps, breakpoints, live variables.
Undetectable cloud browser sessions for AI agents and scrapers. Navigate, extract, click, captcha.
Measure Core Web Vitals and debug web performance with 56 snippets in a headless Chromium
Camoufox browser automation for agents, derived from camoufox-mcp (MIT; MCP stdio + HTTP/REST server, persistent profiles, flows, cron, live view)
Selenium WebDriver MCP Server
MCP server that adds range-anchored (inline) comments to Google Docs — the one comment operation the Google Docs/Drive APIs cannot do — by driving a real logged-in Docs session with Playwright.
Headless browser for AI agents: passes Cloudflare challenges and reads pages as Markdown.
Programmatic headless browser sessions: create, interact, browse, and extract - rendered in a real
Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
Browser automation MCP server: navigate, fill forms, click, screenshot, and manage tabs
Browser automation for AI agents: compressed page snapshots, batched actions, fewer tokens.
Advanced Playwright Tools for MCP
MCP server for the @agentutility browser-workflow cluster — pay-per-call x402 tools, no API keys…
Browser automation: navigate, click, fill, screenshot and evaluate in a headless browser.
Agent-neutral Windows and Chromium computer-use runtime for Claude Code, Qoder, Pi, DeepSeek Harness, and other MCP or CLI hosts.
Sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows
Provider-neutral Chromium and Firefox browser automation for MCP, OpenCode V2, Codex, and direct JavaScript agents.
Windows computer use for DeepSeek Harness: an MCP stdio server + PowerShell UIA backend, bridged into DSH via @deepseek-ai/dsh-mcp-client. Read/act on real Windows desktop apps (UI Automation tree, sc
MCP server for browser automation using Playwright with profile management, page registry, and multi-browser support
Reticle browser SDK — installs observers, builds semantic snapshots, executes actions, talks to the bridge.
Cross-platform testbench for desktop browsers, iOS simulators and devices, and Android emulators and devices
Model Context Protocol server for NexBrowser environment management and browser automation
Scaffold runnable Playwright TypeScript tests from Gherkin .feature files. Detects existing Page Objects, scans live pages via Microsoft Playwright MCP, emits POMs + specs, ready for execution. CLI +
MCP server exposing full Chrome DevTools Protocol debugging: breakpoints, stepping, call stacks, eval, and source maps. Also supports tab control, JS execution, screenshots, and network monitoring.
MCP server for fetching web content using Playwright browser
Control remoto de navegadores Chromium (Brave, Chrome, Edge) via IPC + CDP dinamico. Un comando para conectar Claude Code a tu navegador real.
MCP server for walkerOS data-elb HTML tagging — generate, parse, and validate tracking attributes with real DOM parsing
Scoped, audited SSH exec, sessions, and SFTP on your saved servers without exposing credentials
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Chrome extension that bridges AI agents to web applications through the user's authenticated browser session
Local screen and activity knowledge graph, served as context to computer-use agents.
Evidence-grounded web research: verify claims on pages with citations, confidence bands and policy reports, and synthesize multi-page sessions.
Let any AI assistant drive and scrape your existing Chrome profile — no headless browser, no complex setup.