Skip to main content

MCP Test Architect

The QA Hub Test Architect is a Model Context Protocol (MCP) server that lets AI coding assistants — such as Claude Code or Claude Desktop — autonomously generate, manage, and execute E2E test suites for your application.

Instead of manually writing test cases, you point the Architect at your codebase and it:

  1. Scans your file tree and discovers routes, features, and API endpoints
  2. Generates a structured test plan with BDD scenarios
  3. Writes Playwright TypeScript spec files grounded in real DOM locators
  4. Executes the tests and ingests results into QA Hub
  5. Optionally generates k6 load test scripts

How it relates to QA Hub

The MCP Architect is a client of QA Hub's public API. It uses an API token (qh_*) to:

  • Push generated test cases to your project
  • Submit test plans for QA Manager review
  • Ingest Playwright execution results

All data flows through your QA Hub instance — the Architect itself holds no state.

Available tools

The MCP exposes 16 tools to the AI agent:

ToolDescription
analyze_architectureScan codebase → structured feature/route map
generate_planGenerate BDD test plan from architecture
generate_specsWrite Playwright spec files from plan + locators
generate_k6_scriptGenerate k6 load test script
setup_playwrightInstall and configure Playwright in the target project
crawl_appBrowse the running app to collect DOM locators
save_auth_sessionSave authenticated browser state for test fixtures
execute_playwrightRun Playwright specs and capture results
syncPush test cases to QA Hub library
write_planSave test plan locally as plan.md
write_specsWrite spec files to disk
load_ticketsFetch tickets from the configured connector
select_test_strategyChoose testing strategy (regression, smoke, etc.)
enrich_planRefine an existing test plan
run_full_cycleExecute the complete generate → test → ingest pipeline
bootstrapInitialize the Architect in a target project

Next steps