Playwrightgen
Approved test intent, reviewed Playwright automation and run evidence, inside your editor.
- Transport
- Not stated
- Package
- —
- Registry id
- com.playwrightgen/playwrightgen
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
PlaywrightGen connects to GitHub Copilot, Cursor, or Claude Code to let the assistant write tests from real pages and run them until they pass. It generates test drafts by opening pages in a remote browser and building locators from real buttons, fields, and test attributes. It replays tests step by step on the live page and returns the failing step with the page state, enabling the assistant to fix locators and rerun.
PlaywrightGen offers eleven tools over the Model Context Protocol. Proposals for test cases wait for a person on the team to approve them; nothing counts as coverage until approved. Test execution reads tests into safe Playwright steps and replays them in a remote browser only on public pages.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.