Playwright wrapper for MCP (Model Context Protocol). This server enables LLM-powered clients to control a browser for automation tasks.
Playwright wrapper for MCP (Model Context Protocol). This server enables LLM-powered clients to control a browser for automation tasks. Exposed over MCP by the playwrite mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
Everything the assistant can do here goes through one of these:
navigate — Go to a specific URLnew_page — Create a new browser page with a specific IDswitch_page — Switch to a different browser pageget_pages — List all available browser pagesclick — Click on an element using CSS selectortype — Type text into an input elementwait_for_selector — Wait for an element to appear on the pageget_text — Get text content from an elementget_page_content — Get the entire page HTMLtake_screenshot — Capture visual state of the page or elementResources — The server exposes resources for accessing browser screenshots: - Screenshot resource URI: screenshot://{page_id} - Screenshot resources arePrompts — The server provides a prompt to help clients interpret web pages: - interpret-page: Analyzes the current web page content and structure - Optional@modelcontextprotocol/inspector on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
You will need one environment variable: UV_PUBLISH_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of browser automation servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Playwrite MCP's toolset — navigate, new_page, switch_page and 11 more — is a fair guide to whether it matches your workflow. It is maintained by misanthropic-ai; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| navigate | Go to a specific URL |
| new_page | Create a new browser page with a specific ID |
| switch_page | Switch to a different browser page |
| get_pages | List all available browser pages |
| click | Click on an element using CSS selector |
| type | Type text into an input element |
| wait_for_selector | Wait for an element to appear on the page |
| get_text | Get text content from an element |
| get_page_content | Get the entire page HTML |
| take_screenshot | Capture visual state of the page or element |
| Resources | The server exposes resources for accessing browser screenshots: - Screenshot resource URI: screenshot://{page_id} - Screenshot resources are automatically available for all open pages |
| Prompts | The server provides a prompt to help clients interpret web pages: - interpret-page: Analyzes the current web page content and structure - Optional page_id argument to select which page to interpret - Optional focus argum |
| Tools | The server implements a comprehensive set of browser automation tools: |
| Debugging | Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector). |
{
"mcpServers": {
"playwrite": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/inspector"],
"env": {
"UV_PUBLISH_TOKEN": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| UV_PUBLISH_TOKEN | Credential the server authenticates with. | Yes |
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.