codegen

MCP tool from Mk Qa Master by kao273183

Launch Playwright codegen (web) / hint to maestro studio (mobile)

How to use it

codegen is exposed by the Mk Qa Master MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the codegen tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Mk Qa Master

$pip install mk-qa-master # or: pip install -e . from a clone

FULL MK QA MASTER LISTING

Other tools in Mk Qa Master (14)

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

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)