---
title: "Agentic partners integration: AI support agents for Microsoft Azure Red Hat OpenShift"
description: "The operations team troubleshooting production issues on Azure Red Hat OpenShift must already know which tools to reach for, switching between portals, CLI, and dashboards, with tickets arriving incomplete and triage taking hours. The agentic-partners-integration quickstart solves this by connecting a central orchestration layer with domain-specific agents, including a Microsoft Azure MCP Server that exposes Azure resource management operations as MCP tools and an agent that discovers them at runtime. In an OOMKilled investigation, the agent correlates resource health, CPU metrics, and recommendations using a discover-then-execute pattern to produce a data-backed diagnosis. Security is layered: the service principal defaults to Azure Reader role, Open Policy Agent policies gate every request, and each tool call is logged for audit. This pattern extends beyond Azure; any infrastructure backend exposing an MCP server can become an agent capability without framework changes."
---

# Agentic partners integration: AI support agents for Microsoft Azure Red Hat OpenShift

[Red Hat](https://yomu.fyi/company/red-hat) · Sharon Dashet, Carlos Camacho Gonzalez · Oct 22, 2026

**Type:** Explainer

## Summary

The operations team troubleshooting production issues on Azure Red Hat OpenShift must already know which tools to reach for, switching between portals, CLI, and dashboards, with tickets arriving incomplete and triage taking hours. The agentic-partners-integration quickstart solves this by connecting a central orchestration layer with domain-specific agents, including a Microsoft Azure MCP Server that exposes Azure resource management operations as MCP tools and an agent that discovers them at runtime. In an OOMKilled investigation, the agent correlates resource health, CPU metrics, and recommendations using a discover-then-execute pattern to produce a data-backed diagnosis. Security is layered: the service principal defaults to Azure Reader role, Open Policy Agent policies gate every request, and each tool call is logged for audit. This pattern extends beyond Azure; any infrastructure backend exposing an MCP server can become an agent capability without framework changes.

## Context

Operations teams troubleshooting production issues on Azure Red Hat OpenShift face a bottleneck: tickets arrive incomplete, triage requires switching between multiple tools, and static knowledge bases cannot reflect live infrastructure state. The agentic-partners-integration quickstart addresses this with a multi-agent system that enables live system inspection through MCP servers.

## Approach / What changed

The quickstart adds two components: a containerized Microsoft Azure MCP Server that exposes Azure resource management operations as MCP tools over HTTP, and an Azure Red Hat OpenShift partner agent that discovers these tools at runtime, invokes them in a connect-reason-execute-iterate loop using OpenAI-compatible models, and synthesizes results. Security is enforced through Azure Reader role, OPA authorization, and audit logging. Deployment requires enabling the MCP lifecycle operator and gateway operator on OpenShift AI, then deploying the MCP server from the catalog.

## Takeaways

- The agent uses a discover-then-execute pattern: it first calls a tool to learn its sub-commands, then calls it again with specific parameters, navigating Azure’s tool hierarchy without memorizing every operation.
- Security for the Azure MCP agent is layered: the service principal defaults to Azure Reader (read-only), OPA policies gate every request before dispatch, and each tool call is logged with arguments and results for audit.
- The MCP integration pattern is not Azure-specific; any infrastructure backend exposing an MCP server can become a new agent capability without framework changes, enabling ISVs to collaborate without cross-team coordination.

## FAQ

### How does the agent ensure it only has read access?

The Microsoft Azure Red Hat OpenShift agent uses a service principal with the Azure Reader role by default, providing read-only access to the management plane. Permissions can be further scoped to specific resource groups in production deployments, preventing any modification of infrastructure.

### Can I use a local LLM instead of a cloud API?

Yes, the agent uses OpenAI-compatible API models, allowing the backend to be swapped via a single environment variable. Ollama works for a fully local option with no API key required.

### What happens if the agent needs to investigate resources not covered by Azure?

The same architecture works for any infrastructure backend that exposes an MCP server. Each new MCP server becomes a potential agent capability with no framework changes, and ISVs can contribute tools independently.

**Tags:** [Agentic Development](https://yomu.fyi/topic/agentic-development), [AI Agents](https://yomu.fyi/topic/ai-agents), [Azure](https://yomu.fyi/topic/azure), [MCP](https://yomu.fyi/topic/mcp), [Red Hat OpenShift](https://yomu.fyi/topic/red-hat-openshift)

- Source: [Red Hat](https://developers.redhat.com/articles/2026/10/22/agentic-partners-integration-ai-support-agents-for-microsoft-azure-red-hat-openshift)
- Source URL: https://developers.redhat.com/articles/2026/10/22/agentic-partners-integration-ai-support-agents-for-microsoft-azure-red-hat-openshift
- Ingested by Yomu: 2026-10-22T15:00:15.937Z

[Read original post](https://developers.redhat.com/articles/2026/10/22/agentic-partners-integration-ai-support-agents-for-microsoft-azure-red-hat-openshift)
