// SCAN REPORT

Mk Qa Master

22 tools. 11 can modify or destroy data without limits.

11 write tools that can modify data. Rate limits recommended.

Last updated: 11 Jun 2026

11 can modify or destroy data

11 read-only

22 tools total

Community server · catalogue entry verified 11/06/2026

How to control Mk Qa Master ↓

TOOL MAP

What Mk Qa Master exposes to your agents

Read (11) Write / Execute (11) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Mk Qa Master tools

Execute · High run_api_security_scan This tool executes an external security scanning operation (OWASP API Security Top 10 rule-based scanner) against specified targets. Execute · High run_failed This tool triggers execution of arbitrary test code whose behavior and side effects depend entirely on test implementation. Execute · High run_tests This tool triggers external operations (test execution) whose side effects are determined by the test suite contents and runtime environment. Execute · High auto_generate_tests This tool triggers a multi-step automated pipeline: it first probes/analyzes a URL and then generates and potentially executes test cases for each detected module.

11 of Mk Qa Master's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mk Qa Master

PolicyLayer is an MCP gateway — it sits between your AI agents and Mk Qa Master, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "init_qa_knowledge": {
    "limits": [
      {
        "counter": "init_qa_knowledge_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_screen": {
    "limits": [
      {
        "counter": "analyze_screen_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mk Qa Master — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MK QA MASTER →

Free to start. No card required.

FULL CATALOGUE

All 22 Mk Qa Master tools

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

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

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

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mk Qa Master

How do I prevent bulk modifications through Mk Qa Master? +

The Mk Qa Master server has 4 write tools including init_qa_knowledge, generate_html_report, generate_test. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mk Qa Master.

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

22 tools across 3 categories: Execute, Read, Write. 11 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Mk Qa Master? +

Register the Mk Qa Master MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mk Qa Master tool call.

Deterministic rules across all 22 Mk Qa Master tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MK QA MASTER →

Free to start. No card required.

22 Mk Qa Master tools catalogued and risk-classified — across an index of 43,000+ MCP servers.