Bridging AI and Nomad: a Go-based MCP Server for Cluster Control

In this session, we will explore mcp-nomad, an MCP server written in Go that implements the Model Context Protocol (MCP) to interact with a Nomad cluster.

This project enables access to jobs, nodes, logs, and system metrics through a LLMs. The goal is to demonstrate how artificial intelligence can be connected to real-world infrastructure, providing capabilities such as:

Listing Nomad jobs and nodes Retrieving allocation logs Collecting real-time system metrics running jobs

During the presentation, we will discuss the system architecture, the challenges encountered, and how MCP and skills work, including their core principles and how they enable communication between systems.

A live demo will showcase mcp-nomad integrated into a real-world scenario. The session will conclude with a discussion of the lessons learned.