How does this differ from the upstream Microsoft Playwright MCP server?
This flake wraps the upstream server with NixOS-specific configurations, providing multi-browser support, profile persistence, and a development shell, all managed via Nix.
@benjaminkitt
基本信息
A comprehensive NixOS Flake development environment for the Playwright MCP (Model Context Protocol) server with full Chrome and Firefox support, including persistent browser profiles.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A NixOS Flake development environment for the Playwright Model Context Protocol (MCP) server, providing complete Chrome/Chromium and Firefox browser support with persistent browser profiles. It wraps Microsoft’s official Playwright MCP server with NixOS-specific configurations for developers who want a reproducible setup on NixOS.
Clone or copy flake.nix, then activate with direnv allow or manually with nix develop. Run the server using playwright-mcp-wrapped (headed mode by default) or nix run. Use flags such as --headless, --browser firefox, --config /path/to/config.json, or --port 8931 for server mode. Import desktop profiles by running nix run .#setup-profiles.
This flake wraps the upstream server with NixOS-specific configurations, providing multi-browser support, profile persistence, and a development shell, all managed via Nix.
Chrome/Chromium and Firefox are included as Nix packages and properly configured for Playwright. You can specify the browser with the `--browser` flag.
Browser profiles are stored in `~/.local/share/playwright-mcp/` – Chrome/Chromium under `chrome-profile` and Firefox under `firefox-profile`.
Run `nix run .#playwright-mcp -- --browser chromium` or set `PLAYWRIGHT_BROWSERS_PATH` to the Nix-build path for Playwright browsers.
Remove the profile directory (`~/.local/share/playwright-mcp/`) and rerun `nix run .#setup-profiles` to copy fresh profiles. Ensure the directory is writable with `chmod -R u+w`.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.
Capture screenshots of webpages as images or PDFs with Screenshot Scout.
A flexible HTTP fetching Model Context Protocol server.

An MCP server for generating images from HTML & CSS or screenshots of URLs using htmlcsstoimage.com.
评论