azure

Azure Skills Plugin

Azure work is not just a code problem. It is a decision problem: which service fits this app, what needs to be validated before deployment, which tools should run, and what guardrails matter. The Azure Skills Plugin packages Azure expertise and MCP-backed execution together so compatible coding agents can do real Azure work instead of giving generic cloud advice.

Install the plugin

One install, three layers of capability

Azure skills: the brain

This plugin ships 20 curated Azure skills that teach an agent how Azure work gets done. They provide workflows, decision trees, and guardrails for scenarios such as:

• Build and deploy with azure-prepare, azure-validate, and azure-deploy
• Troubleshoot and operate with azure-diagnostics, azure-observability, and azure-compliance
• Optimize and design with azure-cost-optimization, azure-compute, and azure-resource-visualizer
• Work across data, AI, and platform services with azure-ai, azure-aigateway, azure-storage, azure-kusto, azure-rbac, azure-cloud-migrate, entra-app-registration, and microsoft-foundry

Azure MCP Server: the hands

The plugin wires in the Azure MCP Server, which gives your agent 200+ structured tools across 40+ Azure services. That is the execution layer for listing resources, checking prices, querying logs, diagnosing issues, and driving real Azure workflows.

Foundry MCP: the AI specialist

The plugin also includes Foundry MCP for Microsoft Foundry scenarios such as model discovery, model deployment, and agent workflows.

Why this plugin is different

This is not a prompt pack. It is a packaged Azure capability layer:

• Skills teach the agent when to use Azure workflows and what to avoid.
• MCP tools let the agent act on live Azure and Foundry resources.
• The plugin keeps the guidance layer and execution layer aligned in one install.
• Multi-host support lets you use the same Azure capability across environments such as GitHub Copilot in VS Code, Copilot CLI, Claude Code, and other compatible hosts.

What you get

Component	What it adds	Examples
Azure skills	Azure expertise, workflows, and guardrails	Prepare, validate, deploy, diagnostics, cost, AI, RBAC
Azure MCP Server	Live Azure tooling	Resource inventory, monitoring, pricing, storage, databases, messaging
Foundry MCP	Microsoft Foundry workflows	Model catalog, deployments, agents, evaluations

The plugin payload lives in .github/plugins/azure-skills/, and the included MCP configuration shows how Azure and Foundry connectivity are wired for compatible hosts.

Install in 60 seconds

Prerequisites

Before you install, make sure you have:

• An Azure account or subscription
• Node.js 18+ available on your PATH (npx is used to start the MCP servers)
• Azure CLI installed and authenticated with az login
• Azure Developer CLI installed and authenticated with azd auth login if you plan to use deployment workflows

GitHub Copilot CLI

Add the marketplace (first time only):

/plugin marketplace add microsoft/azure-skills

Install the plugin:

/plugin install azure@azure-skills

Update the plugin:

/plugin update azure@azure-skills

VS Code

Install the Azure MCP extension from the Visual Studio Marketplace:

👉 Azure MCP Extension

The Azure MCP extension will also install a companion extension that brings the Azure skills into VS Code. Together they configure the Azure MCP Server, Foundry MCP, and the full skills layer automatically.

Note: The skills extension requires Git CLI to be installed on your machine. If you don't have it, ask Copilot to help you install Git for your OS.

Claude Code

Add the marketplace (first time only):

/plugin marketplace add microsoft/azure-skills

Install the plugin:

/plugin install azure@azure-skills

Update:

/plugin marketplace update azure-skills

Gemini CLI

Install the extension:

gemini extensions install https://github.com/microsoft/azure-skills

IntelliJ IDEA

Prerequisites

Before installing Azure skills in IntelliJ IDEA, ensure you have:

• Node.js 18+ installed on your system with npx available on your PATH
• Git installed and accessible from the command line

You can verify these prerequisites by running:

npx --version
git --version

Step 1: Install GitHub Copilot Plugin

1. Open IntelliJ IDEA
2. Go to File > Settings (on Windows/Linux) or IntelliJ IDEA > Preferences (on macOS)