Series introduction
As more organizations move from AI experimentation to real-world deployment, one thing becomes clear very quickly: building an AI agent is the easy part. Making that agent useful, scalable, and trustworthy in an enterprise environment is the real challenge.
The moment an AI agent can access data, call APIs, and take action on infrastructure, it's no longer just a prototype, it’s part of the operational stack. This prompts important questions around access control, data governance, observability, and recovery.
This series walks through what it actually takes to run AI agents effectively on NetApp, starting with the fundamentals of AI agents and MCP, then expanding to how NetApp enables and secures these workflows with ONTAP APIs, MCP, RBAC, OAuth-based access, immutable protection, and full auditability.
I'm breaking things down into 4 parts, each building on the one before:
A quick note: There are other AI agent communication protocols— A2A (Google), ACP (Cisco/IBM), ANP, and others — but for this series, we'll focus on MCP (Model Context Protocol), which has emerged as the most widely adopted standard for connecting AI agents to tools and data sources.
At the end of the day, I want to simplify this and frame the architecture around three core components:
- 🧠 The Brain → The AI Agent
- 🤲 The Hands → MCP (Model Context Protocol)
- 🛡️ The Shield → The NetApp data and security foundation
Understanding how these three pieces work together is the key to making AI not just powerful, but safe and operational.
just powerful — but safe, governed, and operational.
Here are links to all the parts of this blog series.
Part 1 — What an AI agent actually is, and why the data layer decides whether it succeeds
Part 2 — What is an MCP Server and why does it matter?
Part 3 — How NetApp empowers AI Agentic workflows
Part 4 — Configuring your NetApp infrastructure for AI agents