QA MCP

🚀 AI-Assisted Network Testing Vibe

An AI-driven network testing tool designed to seamlessly integrate with AI coding assistants like GitHub Copilot. It enables users to control agents via natural language instructions through the MCP protocol for complex network testing tasks.

✨ Features

• Automated Test Recording: Automatically execute network interaction operations via simple text instructions.
• Regression Test Execution: Run saved test files and generate detailed execution reports.
• Test Step Discovery: Intelligently analyze website structures and recommend test steps.
• MCP Protocol Support: Deeply integrate with AI coding assistants to provide efficient development assistance.

📦 Installation

Prerequisites

• Python version 3.10 or higher.
• Access to an LLM (it is recommended to use gemini 2.0 flash).
• Install MCP (pip install mcp[cli]).
• Install the Playwright browser (playwright install).

Steps

1. Clone the repository:

   git clone <repository-url>
   cd <repository-name>
   

2. Create a virtual environment (recommended):

   python -m venv venv
   source venv/bin/activate # Linux/macOS
   # venv\Scripts\activate # Windows
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Install the Playwright browser:

   playwright install --with-deps # Install browser and OS dependencies
   

Configuration

1. Rename the .env.example file to .env in the project root directory.
2. Add the LLM API key and other necessary information:

   # .env
   LLM_API_KEY="YOUR_LLM_API_KEY"
   

   • Replace YOUR_LLM_API_KEY with your actual key.

Adding MCP Server Configuration

Add the following to your MCP configuration:

{
  "mcpServers": {
    "Web-QA":{
      "command": "uv",
      "args": ["--directory","path/to/cloned_repo", "run", "mcp_server.py"]
    }
  }
}

Keep this server running for interaction with the AI coding assistant.

💻 Usage Examples

Basic Usage

Interact with the agent using natural language through your MCP-enabled AI coding assistant.

Example Usage:

• Record a Test:

  "Go to https://practicetestautomation.com/practice-test-login/, enter 'student' in the username field, enter 'Password123' in the password field, click the submit button, and verify that the text 'Congratulations student' is visible."

  • (The agent will automatically perform these actions and save a test_....json file in the output/ directory.)
• Execute a Test:

  "Run the regression test output/test_practice_test_login_20231105_103000.json"

  • (The agent will execute the steps in the specified file and report the PASS/FAIL status, including errors and detailed information.)
• Discover Test Steps:

  "Discover potential test steps starting from https://practicetestautomation.com/practice/."

  • (The agent will crawl the website, analyze the pages, and return recommended test steps for each page.)
• List Recorded Tests:

  "List available recorded network tests."

  • (The agent will return a list of .json files in the output/ directory.)

Output Results:

• Recorded Tests: Saved in JSON format in the output/ directory (see test_schema.md for the format).
• Execution Results: Returned as a JSON object containing status, errors, and detailed information.
• Discovered Steps: Generate structured test step documentation.

📚 Documentation

Project Structure

.
├── README.md          # Project description
├── mcp_server.py     # MCP server implementation
├── requirements.txt  # Dependency list
└── .env.example      # Environment variable example

References

• MCP Protocol Documentation
• Playwright Official Documentation
• AI Coding Assistant Integration Guide

📄 License

[Project license information]

Contributors

[List of contributors]

This tool aims to provide developers with an efficient and intelligent network testing assistance system, significantly improving testing efficiency through AI and automation technologies.