Playwright MCP with video recording capabilities
Playwright Record MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Playwright MCP with video recording capabilities.
Playwright Record MCP is a Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server adds video recording functionality to record browser interactions. It enables LLMs (Large Language Models) to interact with web pages through structured accessibility snapshots, without requiring screenshots or visual models.
Once Playwright Record MCP is connected, these are the calls the assistant has available:
browser_record_start — Description: Start recording browser interactionsParameters — - path (string, optional): Path to save the recording filebrowser_record_stop — Description: Stop and save browser interaction recordingbrowser_record_pause — Description: Pause the current recordingbrowser_record_resume — Description: Resume a paused recordingbrowser_record_list — Description: Return a list of current recording filesbrowser_install tool to install it)Installation goes through your MCP client rather than a global install: point it at @playwright/record-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
This sits in the browser automation group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Playwright Record MCP's toolset — browser_record_start, Parameters, browser_record_stop and 3 more — is a fair guide to whether it matches your workflow. It is maintained by korwabs; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Playwright Record MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| browser_record_start | Description: Start recording browser interactions |
| Parameters | - path (string, optional): Path to save the recording file |
| browser_record_stop | Description: Stop and save browser interaction recording |
| browser_record_pause | Description: Pause the current recording |
| browser_record_resume | Description: Resume a paused recording |
| browser_record_list | Description: Return a list of current recording files |
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/record-mcp@latest",
"--headless"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
browser_install tool to install it)Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.