Software & DevOpsDone with Claude Code Oct 5, 2026
Write Playwright tests with Playwright MCP and Claude Code
A walkthrough of using Playwright MCP with Claude Code to generate Playwright tests in minutes.
- What They Did
- The Playwright MCP server is registered with Claude Code, loaded with a saved logged-in session through storage state. A three-part prompt carries the environment facts, a plain-English scenario, and standing rules. The agent explores the live app through the accessibility tree, writes the test, runs it, and fixes failures itself. A person reviews the code and the scenario's meaning.
- How It Went
- The agent produced a runnable test with locators read from the live page. It also fixed a strict-mode locator error on its own. It struggles with long flows, changing data, deep conditionals, and OAuth. The source gives no timing numbers.
- Worth Knowing
- Add .auth/ to .gitignore before committing, because this setup saves the session outside Playwright's default ignored path, and run the test with --repeat-each 5 to check for flakiness.
Try it yourself with Claude Code
Set up Playwright MCP in this project, then open [app URL] and explore the flow for [user journey, e.g. sign up and checkout]. Write Playwright tests that cover it using stable locators, and run them until they pass. Finish by showing me the test files and the passing run output.