Qainsights K6 MCP Server

🚀 k6-mcp-server

An implementation of the Model Context Protocol (MCP) server for running k6 load tests.

✨ Features

• Simple integration into the Model Context Protocol framework.
• Support for customizing test duration and the number of virtual users (VUs).
• An easy-to-use API for running k6 load tests.
• Configuration via environment variables.
• Real-time test execution output.

🔧 Prerequisites

Before you start, make sure you have installed the following:

• Python 3.12 or higher.
• The k6 load testing tool (Installation Guide).
• The uv package manager (Installation Guide).

📦 Installation

1. Clone the repository:

git clone https://github.com/qainsights/k6-mcp-server.git

2. Install the required dependencies:

uv pip install -r requirements.txt

3. Set environment variables (optional): Create a .env file in the project root directory:

K6_BIN=/path/to/k6  # Optional: Defaults to 'k6' in the system PATH

🚀 Quick Start

1. Create a k6 test script (e.g., test.js):

import http from "k6/http";
import { sleep } from "k6";

export default function () {
  http.get("http://test.k6.io");
  sleep(1);
}

2. Configure the MCP server in your preferred MCP client (e.g., Claude Desktop, Cursor, Windsurf, etc.) with the following specifications:

{
  "mcpServers": {
    "k6": {
      "command": "/path/to/bin/uv",
      "args": [
        "--directory",
        "/path/to/k6-mcp-server",
        "run",
        "k6_server.py"
      ]
    }
  }
}

3. Now, let the LLM run the test, for example, Run a k6 test on hello.js. The k6 MCP server will start the test using one of the following tools:

• execute_k6_test: Run the test with default options (duration of 30 seconds, 10 VUs).
• execute_k6_test_with_options: Run the test with custom duration and number of VUs.

📝 API Reference

Execute a k6 Test

execute_k6_test(
    script_file: str,
    duration: str = "30s",  # Optional, defaults to "30s"
    vus: int = 10          # Optional, defaults to 10
)

Execute a k6 Test with Custom Options

execute_k6_test_with_options(
    script_file: str,
    duration: str,
    vus: int
)

✨ Use Cases

• Conduct result analysis via LLM.
• Effectively debug load tests.

🤝 Contributing

Contributions are welcome! Feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.