Playwright Report Mcp

Built for AI agents analyzing test failures after the fact, not driving browsers. This server runs your Playwright test suite via `run_tests`, reads the JSON reporter output, and surfaces only what matters: failed test details, error messages, and attachment content through `get_failed_tests` and `get_test_attachment`. The token savings are real: fetching failures from an existing run costs around 300 tokens versus 12,000+ for parsing the full results.json yourself. Designed for CI workflows where tests already ran and you need structured failure data without re-running or parsing megabytes of HTML reports. Requires the Playwright JSON reporter configured in your project.