playwright-e2e-mcp

Playwright end-to-end testing MCP server — run, debug and inspect E2E tests from any AI agent: failure analysis, live DOM inspection, selector validation, visual diffs, flaky-test diagnosis.

Playwright

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

模型生成摘要（rules/v1 · 2026-10-16 14:36）：Playwright end-to-end testing MCP server — run, debug and inspect E2E tests from any AI agent: failure analysis, live DO…
这是模型对公开材料的总结，不是官方声明，请以原链内容为准。

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://playwright-e2e-mcp--trajectiq.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "playwright-e2e-mcp": {
      "url": "https://playwright-e2e-mcp--trajectiq.run.tools"
    }
  }
}

能力清单

工具	说明
run-test	Run Playwright end-to-end tests in the user's project and return structured results: pass/fail stats, per-failure messages with file:line, and diagnostics. Detects missing Playwright installs, multiple configs, dead dev servers, syntax errors, browser crashes, timeouts (kills the process tree and returns partial results) and full disks.
get-failure	Analyze one failure from the most recent run-test execution: full message and code frame, expected vs actual, stack trace, failed network requests (4xx/5xx and dead endpoints), console errors, failure kind (assertion/timeout/browser-crash/syntax/config/server-unreachable) and concrete next steps. Use run-test first.
inspect-page	Open a URL in a headless browser and return the rendered DOM: elements with unique CSS selectors, visibility, bounding boxes, text, attributes, captured console messages and optional HTML. Use this to understand a live page before writing or fixing selectors/tests. Requires a reachable URL (detects a missing dev server).
list-tests	List the Playwright tests available in the project (file, line, full title, projects), with optional filtering. Uses `playwright test --list` when Playwright works and falls back to a source scan when the install or config is broken, reporting why.
validate-selector	Check a CSS selector against a live page: syntax validity, match count, and a sample of matched elements (tag, visibility, box, text). Also flags Playwright-only selector engines (text=, xpath=, >>, :has-text()) that are not valid CSS.
generate-e2e-test	Scaffold a Playwright test from a description using the project's REAL selectors. Scans the agent's recent file changes (git working tree / last commit, mtime fallback), extracts data-testid / role / label / placeholder / id locators with their source locations, optionally cross-checks them against the live page, writes a ready-to-run spec, and returns next steps.
compare-visual-state	Visual regression check: screenshot a live page (or element), compare it to a stored baseline, and report how many pixels changed, WHERE they changed (bounding regions), and the average color shift ("blue → red"). First call saves the baseline; later calls compare. Writes a red-highlighted diff image for review.
diagnose-flaky	Run a failing test multiple times with retries disabled and return an evidence-based verdict: CONSISTENTLY FAILING (real bug), FLAKY (intermittent — includes pass/fail counts and error-signature variance) or NOT REPRODUCING (one-off). Defaults to the tests that failed in the most recent run.

playwright-e2e-mcp

接入信息

能力清单

相关资产

rove

playwright-browser

autoapply-mcp

TestForge - Autonomous Full-Stack QA, E2E Playwright & Vitest Engine MCP

Playwright 网页自动化工具

axelhu-playwright-scrape