
User stories to verified Playwright tests, and self-healing locators with an audit trail.
Public tool metadata for what this MCP can expose to an agent.
explore_pageOpens a URL and lists elements with locators verified to match exactly one element.Opens a URL and lists elements with locators verified to match exactly one element.
No parameter schema in public metadata yet.
check_locatorCounts what a locator matches on a page (1 = good) and whether it's visible.Counts what a locator matches on a page (1 = good) and whether it's visible.
No parameter schema in public metadata yet.
parse_user_storyUser story → structured scenarios + a Playwright Test skeleton.User story → structured scenarios + a Playwright Test skeleton.
No parameter schema in public metadata yet.
write_testWrites a spec into `tests/`. Refuses paths outside it; won't overwrite unless asked.Writes a spec into `tests/`. Refuses paths outside it; won't overwrite unless asked.
No parameter schema in public metadata yet.
run_testsRuns Playwright Test and returns per-test results with the failing locator.Runs Playwright Test and returns per-test results with the failing locator.
No parameter schema in public metadata yet.
capture_baselineWhile tests pass, fingerprints the element each locator matches (`.qa-mcp/baselines.json`).While tests pass, fingerprints the element each locator matches (`.qa-mcp/baselines.json`).
No parameter schema in public metadata yet.
heal_locatorFinds the intended element after a UI change and suggests a verified replacement.Finds the intended element after a UI change and suggests a verified replacement.
No parameter schema in public metadata yet.
save_login_stateLogs in once with a few steps and saves the session for the other tools and your tests.Logs in once with a few steps and saves the session for the other tools and your tests.
No parameter schema in public metadata yet.
Sponsors
QA_MCP_ROOTFolder of the project under test (defaults to the current directory)
Turn user stories into Playwright tests that actually pass, and fix the ones a redesign just broke.
AI coding assistants write Playwright tests quickly, but they guess selectors. The tests look right, then fail on the first run, or break the next time someone renames a CSS class. This MCP server gives the assistant the facts it can't guess:
getByTestId, getByRole, getByLabel, ...).test.step per step.k11-playwright-qa-mcp