Netdata AI Now Talks to Your Other Tools to Find Root Cause Faster — and Explain the 'Why' Behind the 'What'

What You'll Learn

An alert tells you what changed. It rarely tells you why. That answer usually lives somewhere else: the pull request that shipped minutes earlier, the incident already open in PagerDuty, the runbook sitting in Confluence. Netdata AI can now reach those systems directly. Through the Model Context Protocol, it connects to the tools your team already runs and reads from them while it investigates. It pulls that context alongside the metrics, logs, and anomalies Netdata detects on every node, then reasons across both. This closes the gap between the what and the why. Netdata AI correlates a latency spike with the deploy that caused it, ties an anomaly to the incident already tracking it, and surfaces the runbook without you going to look for it. Root cause in one investigation, not five browser tabs. We will show how MCP client support works and how to connect your own tools. Then we will run a live investigation across a connected stack, so you can see the difference between an agent that reports signals and one that can explain them.

Key Takeaways

Why an alert tells you what changed but rarely why — and where that answer actually lives

How Netdata AI uses the Model Context Protocol to read from the tools your team already runs while it investigates

How it pulls that external context alongside the metrics, logs, and anomalies Netdata detects on every node

How MCP client support works, and how to connect your own tools

A live investigation across a connected stack — correlating a latency spike with the deploy that caused it, and tying an anomaly to the incident already tracking it

The difference between an agent that reports signals and one that can explain them