🚀 ⚡️ k6-mcp-server

What is k6-mcp-server?

k6-mcp-server is a Model Context Protocol (MCP) server implementation for running k6 load tests. It allows users to execute performance tests via natural language prompts from an MCP‑compatible client.

How to use k6-mcp-server?

Install Python 3.12+, the k6 load testing tool, and the uv package manager. Clone the repository and run uv pip install -r requirements.txt. Optionally set the K6_BIN environment variable. Configure the server in your MCP client (e.g., Claude Desktop, Cursor) with the command /path/to/bin/uv run k6_server.py. Then ask the LLM to run a test; the server uses the execute_k6_test tool (default: 30s duration, 10 VUs) or execute_k6_test_with_options for custom duration and VUs.

Key features of k6-mcp-server

• Simple integration with the Model Context Protocol framework
• Support for custom test durations and virtual users (VUs)
• Easy-to-use API for running k6 load tests
• Configurable through environment variables
• Real-time test execution output

Use cases of k6-mcp-server

• LLM-powered results analysis
• Effective debugging of load tests

FAQ from k6-mcp-server

What are the prerequisites for using k6-mcp-server?

You need Python 3.12 or higher, the k6 load testing tool, and the uv package manager installed.

How do I install k6-mcp-server?

Clone the repository and run uv pip install -r requirements.txt in the project directory.

How do I run a k6 test with custom duration and virtual users?

Use the execute_k6_test_with_options tool, providing the script file, duration (e.g., "60s"), and number of VUs.

What environment variables can I configure?

You can optionally set K6_BIN to specify the path to the k6 binary; it defaults to k6 in the system PATH.