MCP (Model Context Protocol) Support

Starting from the version 2.0.0, Goku integrates with the Model Context Protocol (MCP) — which means you can now use Goku programmatically from an LLM agent or any other MCP-aware client.

MCP is an open standard that allows language models and external tools to interoperate through a unified interface: exposing data sources, file systems, APIs or internal logic as “tools” the model can call.

What this enables

• Use Goku from an LLM or AI agent directly — no manual CLI usage required.
• Combine load testing with automated workflows: for instance, trigger a test, gather metrics, and analyze results from within an agent or script.
• Seamless integration into broader toolchains, pipelines or “agentic” workflows, exploiting Goku’s performance-testing features programmatically.

Example usage with an LLM

Once Goku is registered as an MCP tool, you can ask your LLM something like:

"Run a performance test on https://github.com with 2 concurrent users and a total of 30 requests, and provide the 95th percentile response time."

The LLM will translate this into an MCP tool call, run the test through Goku, and return the structured results.

Automatic download (Linux, OSX, WSL)

You can download the latest version of Goku directly to your current directory with the following command:

curl -sSL https://raw.githubusercontent.com/jcaromiq/goku/v2.0.1/scripts/install_mcp.sh | sh

Using Cargo

...