Test Automator

# Windows set GOOGLE_API_KEY=your_api_key_here # Linux/macOS/WSL export GOOGLE_API_KEY=your_api_key_here

claude mcp add test-automator "/path/to/test-automator/.venv/bin/test-automator" -e "GOOGLE_API_KEY=your_api_key"

Add to your Claude Code configuration (~/.claude.json):

{ "projects": { "/your/project/path": { "mcpServers": { "test-automator": { "type": "stdio", "command": "/path/to/test-automator/.venv/bin/test-automator", "env": { "GOOGLE_API_KEY": "your_api_key_here" } } } } } }

- Windows:C:/path/to/test-automator/.venv/Scripts/test-automator.exe
- WSL:/home/username/test-automator/.venv/bin/test-automator

generate_tests(code_path, test_type="all")

Generate intelligent tests for your codebase:

# Generate all test types generate_tests("/path/to/your/code", "all") # Generate specific test type generate_tests("/path/to/your/api.py", "unit") generate_tests("/path/to/your/project", "integration") generate_tests("/path/to/your/webapp", "e2e") generate_tests("/path/to/your/api", "api")

run_tests(test_type="all", target_path="tests/")

# Run all tests run_tests("all", "/path/to/tests") # Run specific test type run_tests("unit", "/path/to/tests")

Get LLM-powered insights from test results:

analyze_test_report("/path/to/test_results.xml")

# 1. Generate comprehensive tests generate_tests("/home/user/my-project", "all") # 2. Run the tests run_tests("all", "/home/user/my-project/tests") # 3. Analyze results analyze_test_report("/home/user/my-project/tests/results/unit_results.xml")

Large Codebase Support (100k-200k lines)

- Modular Analysis: Processes code in manageable chunks
- Incremental Testing: Generates tests incrementally for better performance
- Parallel Execution: Supports pytest-xdist for parallel test runs
- Smart Filtering: Focuses on testable units to avoid overwhelming LLM

- Windows Native: Full support with proper path handling
- WSL Integration: Seamless Windows Subsystem for Linux support
- Linux/macOS: Native Unix support
- Event Loop Handling: Platform-specific async optimizations

- Async Operations: Non-blocking test execution
- Batch Processing: Efficient handling of multiple test files
- Resource Management: Proper cleanup and memory management
- Timeout Handling: Configurable timeouts for different test types

test-automator/ ├── test_automator/ │ ├── __init__.py │ ├── mcp_server.py # Main MCP server with tools │ ├── test_generator.py # LLM-powered test generation │ ├── test_runner.py # Cross-platform test execution │ └── report_analyzer.py # AI-enhanced report analysis ├── pyproject.toml # Package configuration └── README.md # This file

# Set the environment variable export GOOGLE_API_KEY="your_api_key_here" # Or add to shell profile echo 'export GOOGLE_API_KEY="your_api_key"' >> ~/.bashrc

"Playwright browsers not found"

# Install browsers playwright install # Install system dependencies (Linux) playwright install-deps

# Ensure script execution is enabled Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser # Check virtual environment activation .venv\\Scripts\\activate

# Install X11 server for Windows # Add to ~/.bashrc: export DISPLAY=:0.0

- Fork the repository
- Create a feature branch (git checkout -b feature/amazing-feature)
- Commit your changes (git commit -m 'Add amazing feature')
- Push to the branch (git push origin feature/amazing-feature)
- Open a Pull Request

- Gemini LLM: Google's powerful language model for intelligent test generation
- Playwright: Cross-browser automation framework
- pytest: Robust Python testing framework
- MCP Protocol: Model Context Protocol for seamless AI integration
- Claude Code: AI-powered development environment

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Help agents automatically write and test stories for your UI components

Six read-only decision tools for coding agents to assess GitHub bounties, audit agent instructions, diagnose GitHub Actions failures and flakes, and detect MCP tool drift. Remote Streamable HTTP

AI-Safe Code Analysis with 113+ MCP tools for guard validation, memory, workflow, and testing.

fable-discipline is a Claude Code plugin that makes agentic software work follow repeatable working patterns: design before code, verify after edits, separate author from reviewer, preserve verified state between sessions, and report uncertainty honestly.

MCP server that generates production-grade engineering standards (SOLID, testing, architecture, CI/CD) for AI coding assistants

Execute JavaScript code in a modern runtime environment with support for various built-in modules.

Provides a secure JavaScript execution environment for running code snippets.

A server for JavaScript/TypeScript development with intelligent project tooling and testing capabilities.

Execute code securely in isolated sandbox environments using the E2B API.