Mk Qa Master
未认领AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/Android/BlueStacks).
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'mk-qa-master' -- 'uvx' 'mk-qa-master'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多Search & Web服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
15 个工具中显示 15 个
文档中列出的工具 (15)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
analyze_screen
Mobile: maestro hierarchy → form / cta / tabbar modules + candidate TCs (noise-filtered)
analyze_url
Web: DOM probe → modules + selectors + candidate TCs + API endpoints + layout overflow warnings
auto_generate_tests
One-shot: analyze URL → generate one test per discovered module
codegen
Launch Playwright codegen (web) / hint to maestro studio (mobile)
generate_html_report
Render the latest run as self-contained HTML
generate_test
Test skeleton; with module from analyzeurl/analyzescreen, a runnable one (Playwright .py or Maestro .yaml)
get_failure_details
Per-failure message + screenshot / trace / video paths
get_optimization_plan
Three-layer self-improvement coach (suite / MCP / AI strategy)
get_runner_info
Which runner is active + all available ones
get_test_history
Last N archived run summaries (for trend / flake debugging)
get_test_report
Summary (pass / fail / skipped / duration / flaky-in-run)
list_tests
Enumerate tests in the project
run_api_security_scan
v0.8.0 OWASP API Security Top 10 (2023) rule-based scanner — load an OpenAPI 3.x spec, walk path × method, dispatch 5 in-scope rules (API1 BOLA, API2 Broken Auth, API3 Mass Assignment, API5 Function-Level Authz, API8 Misconfig). Gated by QAAPISECURITYCONSENT=true + QAAPISECURITYAUTHORIZEDDOMAINS. Se
run_failed
Re-run last failures (pytest --lf)
run_tests
Run tests (filter / headed / browser; last two pytest-playwright only)