Playwriter

Active
GitHub HTML MIT

Description

Chrome extension & CLI to let agents control your browser. Runs Playwright snippets in a stateful sandbox. Available as CLI or MCP.

Key Features

  • Connects to your running Chrome browser instead of spawning a fresh instance, preserving logins, extensions, and cookies
  • Full Playwright API access via a single `execute` tool, reducing context usage compared to multi-tool alternatives
  • Vimium-style visual accessibility labels with color-coded element types for AI agent element identification
  • Stateful sandbox sessions with isolated state and shared browser tabs across multiple agents
  • Raw CDP access for debugging, breakpoints, live code editing, and network interception
  • MCP server integration enabling any MCP-compatible agent to control the browser

Use Cases

πŸ’‘ Browser automation for AI agents that need to interact with authenticated web services
πŸ’‘ Web scraping and data extraction from pages requiring existing login sessions
πŸ’‘ End-to-end testing of web applications using real browser environments
πŸ’‘ AI-powered research and information gathering from complex web interfaces
πŸ’‘ Automating form submissions, workflows, and multi-step web interactions

Tags

mcp playwright browser-automation chrome-extension browser-agent

Categories

🌐 Browser Agent πŸ”Œ MCP Tools

Quick Start

1. Install the Chrome extension from the Chrome Web Store
2. Click the extension icon on a tab (turns green when connected)
3. Install the CLI: `npm i -g playwriter`
4. Start automating: `playwriter -s 1 -e 'await page.goto("https://example.com")'`
5. For agent integration, install the skill: `npx -y skills add remorses/playwriter`
Visit GitHub Visit Website

Related Projects