// MCP TOOL REFERENCE

MK QA MASTER TOOLS

22 tools from the Mk Qa Master MCP Server, categorised by risk level.

// ALL 22 MK QA MASTER TOOLS

READ 11 tools

Read analyze_screen Mobile 版的 analyze_url：透過 `maestro hierarchy` dump 當前 iOS Simulator / Read analyze_stream v1.1.0 — Edge AI version of analyze_url / analyze_screen. Probes an Read get_failure_details Extract full root-cause-analysis materials for every failed test in the Read get_optimization_plan 綜合 history/ 快照、telemetry tool-usage、analyze_url 偵測過的 modules， Read get_qa_context 讀取受測專案的 qa-knowledge.md（業務規則 / 歷史 Bug / 標準斷言文字 / Read get_runner_info 回傳目前由 QA_RUNNER 環境變數選定的測試 runner（pytest / jest / cypress / Read get_test_history 遍歷 test-results/history/*.json 快照（每次 run_tests 完會自動歸檔）， Read get_test_report 讀上一次 run_tests 留下的 report.json，回傳一個輕量摘要： Read inspect_visual_challenge Detect a reCAPTCHA v2 image-grid challenge on the active page, screenshot it, Read list_tests 用 runner 的原生 collection 機制列出受測專案內所有可執行測試： Read verify_plan v0.9.1 (extended v0.9.2 with auto-discovery) — Walk a plan

WRITE 4 tools

Write init_qa_knowledge 在受測專案根 (PROJECT_ROOT) 建立 qa-knowledge.md 起手範本， Write generate_html_report 把最近一次 run_tests 的結果渲染成單檔自包含 HTML——base64 內嵌截圖、 Write generate_test 產生 pytest-playwright 測試骨架。 Write qa_plan v0.9.1 — Store a critical-points checklist before acting on a QA

EXECUTE 7 tools

Execute run_api_security_scan v0.8.0: OWASP API Security Top 10 (2023) rule-based scanner. Loads an Execute run_failed 只重跑上次失敗的測試——比跑整套套件快很多，適合修完一個 bug 後驗證迭代。 Execute run_tests Execute the test suite under the active QA_RUNNER and produce a structured Execute analyze_url Probe a live web page in headless Chromium and return a structured map of Execute codegen Launch interactive test recording for the active runner. Useful as a Execute solve_visual_challenge Apply the AI client Execute auto_generate_tests 一鍵交付：在內部依序做 analyze_url → 為每個偵測到的 module 用 candidate_tcs 內容

// FAQ

How many tools does the Mk Qa Master MCP server have? +

The Mk Qa Master MCP server exposes 22 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Mk Qa Master tools? +

Route the Mk Qa Master server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Mk Qa Master tools fall into? +

Mk Qa Master tools are categorised as Read (11), Write (4), Execute (7). Each category has a recommended default policy.

Enforce policy on every Mk Qa Master tool call.

Start from Mk Qa Master, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.