MCP & Semantic Kernel AI Agents: Building IT Ops Automation That Actually Takes Action

MCP & Semantic Kernel AI Agents: Building IT Ops Automation That Actually Takes Action is explained in this M365 FM video guide. Learn the core concepts, key capabilities, practical use cases and implementation considerations for real-world Microsoft environments.

(00:00:00) Transforming AI from Talker to Worker

(00:00:40) The Shift from Q&A to Action

(00:01:50) The Three Ingredients of AI Orchestration

(00:04:30) The Six Parts of a Capable IT OPS Agent

(00:10:08) Microsoft Stack: The Containment Field

(00:16:45) Blueprint I: SK Planner + Graph via MCP

(00:22:32) Blueprint II: Azure Open AI Tool Calling with Managed Identity

(00:27:40) Blueprint III: Incident Autoremediation and IT OPS

(00:35:28) The Power of Guardrails and Responsibility

(00:41:48) Key Takeaways and Future Directions

In this episode of M365.fm, Mirko Peters shows how to turn AI from chatty assistant into a disciplined IT Operations agent that plans, executes, verifies, and stays inside governance—from Semantic Kernel and MCP to Azure OpenAI with Managed Identity.

(https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266) WHAT YOU WILL LEARN

• Why “chatbots that give advice” are wasting your AI potential compared to agents that actually act (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• How to move from Q&A loops to a closed‑loop cycle: Intention → Plan → Tool Use → Result → Self‑Check → Next Step (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• How real SRE teams wire agents to handle incidents end‑to‑end before a human even wakes up (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• How MCP exposes tools like Microsoft Graph, Intune, App Insights, and internal APIs in a standard, discoverable way (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• How Semantic Kernel turns those tools into orchestrated plans with sequential, parallel, and graph‑shaped tasks (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• How Azure OpenAI with Managed Identity keeps credentials out of prompts and enforces RBAC at the tool boundary (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• How to design stable “agent molecules” with persona, memory, planner, tools, policy, and verifier working together (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266) THE CORE INSIGHT

Most AI projects stall at “better answers.” The real value appears when agents are allowed to do work in a closed loop with tools, checks, and guardrails. (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
MCP makes your tools visible, Semantic Kernel orchestrates the plan, Azure OpenAI reasons about steps, and Managed Identity constrains what’s actually allowed. (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
Instead of magic prompts, you get small, testable workflows where every action is logged, validated, and reversible. (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
This episode argues that serious AI in Microsoft shops is not about smarter chat—it is about building verifiable, identity‑bound agents that behave like cautious SREs.

WHY MCP + SEMANTIC KERNEL + MANAGED IDENTITY WORK

• MCP standardizes tool exposure so Graph, Intune, Service Health, and internal services describe themselves via schemas—not ad‑hoc plugins (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• Semantic Kernel wraps MCP tools as functions, builds JSON payloads, and handles planning across multiple steps and branches (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• Azure OpenAI uses tool‑calling while Managed Identity decides what each tool is actually allowed to do (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• High‑risk actions (rollback, redeploy, bulk changes) require explicit approvals encoded in tools, not “pretty please” in prompts (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• Audit envelopes and telemetry turn every tool call into evidence you can review, replay, or red‑team (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266) KEY TAKEAWAYS

• Agents need six parts to stay predictable: persona, memory, planner, tools, policy, and verifier (https://www.spreaker.com/cms/episodes/68796299/edit/info?filter=NETWORK&network=18613266)
• Start with narrow, high‑value flows like post‑deploy