Claude Desktop Cursor Codex CLI Gemini CLI Cline Zed

   [URL]
        │  analyze_url
        ▼
   modules + candidate TCs + API endpoints
        │  generate_test (module=...)
        ▼
   tests/test_*.py   
        │  run_tests
        ▼
   report.json + screenshots + trace.zip + junit.xml
        │
        ├──→ generate_html_report  ──→  
        ├──→ auto archive          ──→  history/ snapshot
        └──→ optimizer auto-write  ──→  optimization-plan.md
                                                 │
                                                 ▼
                                      

1

git clone https://github.com/kao273183/mcp-test-runner.git
cd mcp-test-runner
python -m venv .venv && source .venv/bin/activate
pip install -e .
playwright install chromium
2

{
  "mcpServers": {
    "mcp-test-runner": {
      "command": "/path/to/.venv/bin/python",
      "args": ["-m", "mcp_test_runner.server"],
      "cwd": "/path/to/mcp-test-runner",
      "env": {
        "QA_RUNNER": "pytest",
        "QA_PROJECT_ROOT": "/path/to/your-test-project"
      }
    }
  }
}
3








setup
get_runner_infoinit_qa_knowledgeget_qa_context
execution
list_testsrun_testsrun_failed
authoring
analyze_urlgenerate_testauto_generate_testscodegen
reporting
get_test_reportget_failure_detailsgenerate_html_report
advisor
get_test_historyget_optimization_plan