Add Azure plugin with 21 skills and MCP server configs

Create the 'azure' plugin (plugins/azure/) with plugin metadata,
README, and .mcp.json (azure, foundry-mcp, context7, playwright
MCP servers).

Copy 21 skill folders to skills/ from the github-copilot-for-azure
source repo at commit baca73dadb90dce675c2a99fb01192f1c7ff4e2f.

Skills: appinsights-instrumentation, azure-ai, azure-aigateway,
azure-cloud-migrate, azure-compliance, azure-compute,
azure-cost-optimization, azure-deploy, azure-diagnostics,
azure-hosted-copilot-sdk, azure-kusto, azure-messaging,
azure-observability, azure-prepare, azure-rbac,
azure-resource-lookup, azure-resource-visualizer, azure-storage,
azure-validate, entra-app-registration, microsoft-foundry.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: tmeschter

.github/plugin/marketplace.json

@@ -16,6 +16,12 @@
       "description": "Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.",
       "version": "1.0.0"
     },
+    {
+      "name": "azure",
+      "source": "azure",
+      "description": "Microsoft Azure MCP integration for cloud resource management, deployments, and Azure services. Manage your Azure infrastructure, monitor applications, and deploy resources directly from Claude Code.",
+      "version": "1.0.0"
+    },
     {
       "name": "azure-cloud-development",
       "source": "azure-cloud-development",

docs/README.plugins.md

@@ -0,0 +1,36 @@
+{
+  "name": "azure",
+  "description": "Microsoft Azure MCP integration for cloud resource management, deployments, and Azure services. Manage your Azure infrastructure, monitor applications, and deploy resources directly from Claude Code.",
+  "version": "1.0.0",
+  "author": {
+    "name": "Microsoft",
+    "url": "https://www.microsoft.com"
+  },
+  "homepage": "https://github.com/microsoft/github-copilot-for-azure",
+  "repository": "https://github.com/github/awesome-copilot",
+  "license": "MIT",
+  "keywords": ["azure", "cloud", "infrastructure", "deployment", "microsoft", "devops"],
+  "skills": [
+    "./skills/appinsights-instrumentation/",
+    "./skills/azure-ai/",
+    "./skills/azure-aigateway/",
+    "./skills/azure-cloud-migrate/",
+    "./skills/azure-compliance/",
+    "./skills/azure-compute/",
+    "./skills/azure-cost-optimization/",
+    "./skills/azure-deploy/",
+    "./skills/azure-diagnostics/",
+    "./skills/azure-hosted-copilot-sdk/",
+    "./skills/azure-kusto/",
+    "./skills/azure-messaging/",
+    "./skills/azure-observability/",
+    "./skills/azure-prepare/",
+    "./skills/azure-rbac/",
+    "./skills/azure-resource-lookup/",
+    "./skills/azure-resource-visualizer/",
+    "./skills/azure-storage/",
+    "./skills/azure-validate/",
+    "./skills/entra-app-registration/",
+    "./skills/microsoft-foundry/"
+  ]
+}

docs/README.skills.md

@@ -0,0 +1,20 @@
+{
+  "mcpServers": {
+    "azure": {
+      "command": "npx",
+      "args": ["-y", "@azure/mcp@latest", "server", "start"]
+    },
+    "foundry-mcp": { 
+      "type": "http", 
+      "url": "https://mcp.ai.azure.com" 
+    },
+    "context7": {
+      "command": "npx",
+      "args": ["-y", "@upstash/context7-mcp@latest"]
+    },
+    "playwright": {
+      "command": "npx",
+      "args": ["-y", "@playwright/mcp@latest"]
+    }
+  }
+}

plugins/azure/.github/plugin/plugin.json

@@ -0,0 +1,129 @@
+# Azure
+
+[Microsoft Azure](https://azure.microsoft.com) is Microsoft's cloud computing platform. This plugin connects [GitHub Copilot CLI](https://github.com/github/copilot-cli) or Claude Code to your Azure account, letting you manage resources, deploy applications, and monitor services directly from your development environment.
+
+## Setup
+
+### 1. Create an Azure Account
+
+Sign up at [azure.microsoft.com](https://azure.microsoft.com) or use your existing Azure account.
+
+### 2. Install Node.js and NPM
+
+The Azure MCP Server runs as an NPM package. Ensure you have Node.js 18 or later installed:
+
+- Download from [nodejs.org](https://nodejs.org)
+- Or use a version manager like [nvm](https://github.com/nvm-sh/nvm)
+
+### 3. Authenticate to Azure
+
+The Azure MCP Server uses the Azure Identity SDK for authentication. You can authenticate using any of these methods:
+
+#### Option A: Azure CLI (Recommended)
+1. Install [Azure CLI](https://docs.microsoft.com/cli/azure/install-azure-cli)
+2. Run `az login` to authenticate
+3. The MCP server will automatically use your CLI credentials
+
+#### Option B: Environment Variables
+Set Azure service principal credentials:
+
+**Bash/Zsh:**
+```bash
+export AZURE_TENANT_ID="your-tenant-id"
+export AZURE_CLIENT_ID="your-client-id"
+export AZURE_CLIENT_SECRET="your-client-secret"
+```
+
+**PowerShell:**
+```powershell
+$env:AZURE_TENANT_ID = "your-tenant-id"
+$env:AZURE_CLIENT_ID = "your-client-id"
+$env:AZURE_CLIENT_SECRET = "your-client-secret"
+```
+
+#### Option C: Managed Identity
+When running on Azure resources (VMs, Container Apps, etc.), the server automatically uses managed identity.
+
+For more authentication options, see the [Azure Identity documentation](https://learn.microsoft.com/azure/developer/azure-mcp-server/).
+
+### 4. Install the Plugins
+# Add the repo as a plugin marketplace
+/plugin marketplace add microsoft/github-copilot-for-azure
+
+# Pull in the Azure plugin
+/plugin install azure@github-copilot-for-azure
+
+## Available Tools
+
+The Azure MCP Server provides tools for 40+ Azure services:
+
+### AI & Machine Learning
+- Microsoft Foundry (AI models, deployments, knowledge indexes)
+- Azure AI Search (search and vector database)
+- Azure AI Services Speech (speech-to-text, text-to-speech)
+
+### Compute & Containers
+- Azure App Service, Container Apps, AKS
+- Azure Functions, Virtual Desktop
+
+### Storage & Databases
+- Azure Storage (Blob, File Sync)
+- Azure SQL Database, Cosmos DB
+- Azure Database for MySQL & PostgreSQL
+
+### Security & Networking
+- Azure Key Vault (secrets, keys, certificates)
+- Azure RBAC (access control)
+- Azure Confidential Ledger
+
+### DevOps & Management
+- Resource Groups, Subscriptions
+- Azure Monitor (logging, metrics)
+- Azure CLI command generation
+- Bicep templates
+
+### Messaging & Communication
+- Azure Communication Services (SMS, email)
+- Azure Service Bus, Event Grid
+
+For the complete list of 40+ services, see the [official documentation](https://learn.microsoft.com/azure/developer/azure-mcp-server/).
+
+## Example Usage
+
+Ask GitHub Copilot CLI or Claude Code to:
+- "List my Azure storage accounts"
+- "Show me all containers in my Cosmos DB database"
+- "List all secrets in my key vault 'my-vault'"
+- "Deploy a web app to Azure App Service"
+- "Query my Log Analytics workspace"
+- "List my AKS clusters"
+- "Send an SMS message to +1234567890 using Azure Communication Services"
+- "Generate an Azure CLI command to create a storage account"
+
+For more examples, visit the [Azure MCP documentation](https://learn.microsoft.com/azure/developer/azure-mcp-server/).
+
+## Documentation
+
+For more information, visit:
+- [Azure Documentation](https://docs.microsoft.com/azure)
+- [Azure CLI Reference](https://docs.microsoft.com/cli/azure/)
+- [Azure REST API Reference](https://docs.microsoft.com/rest/api/azure/)
+
+## Troubleshooting
+
+### Authentication Issues
+- Run `az login` to authenticate with Azure CLI
+- Verify you have appropriate Azure RBAC permissions
+- Check that your credentials are not expired
+- See the [Authentication guide](https://learn.microsoft.com/azure/developer/azure-mcp-server/)
+
+### Server Issues
+- Ensure Node.js 18 or later is installed
+- Verify NPM can download packages from npmjs.com
+- Check the [Troubleshooting guide](https://github.com/microsoft/mcp/blob/main/servers/Azure.Mcp.Server/TROUBLESHOOTING.md)
+
+### Telemetry
+To disable telemetry collection, set:
+```bash
+export AZURE_MCP_COLLECT_TELEMETRY=false
+```

plugins/azure/.mcp.json

@@ -1,15 +1,34 @@
 ---
 name: appinsights-instrumentation
-description: 'Instrument a webapp to send useful telemetry data to Azure App Insights'
+description: "Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. USE FOR: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices. DO NOT USE FOR: adding App Insights to my app (use azure-prepare), add telemetry to my project (use azure-prepare), add monitoring (use azure-prepare). This skill provides guidance—azure-prepare orchestrates component changes."
+license: MIT
+metadata:
+  author: Microsoft
+  version: "1.0.0"
 ---
 
-# AppInsights instrumentation
+# AppInsights Instrumentation Guide
 
-This skill enables sending telemetry data of a webapp to Azure App Insights for better observability of the app's health.
+This skill provides **guidance and reference material** for instrumenting webapps with Azure Application Insights.
 
-## When to use this skill
+> **⛔ ADDING COMPONENTS?**
+>
+> If the user wants to **add App Insights to their app**, invoke **azure-prepare** instead.
+> This skill provides reference material—azure-prepare orchestrates the actual changes.
 
-Use this skill when the user wants to enable telemetry for their webapp.
+## When to Use This Skill
+
+- User asks **how** to instrument (guidance, patterns, examples)
+- User needs SDK setup instructions
+- azure-prepare invokes this skill during research phase
+- User wants to understand App Insights concepts
+
+## When to Use azure-prepare Instead
+
+- User says "add telemetry to my app"
+- User says "add App Insights" 
+- User wants to modify their project
+- Any request to change/add components
 
 ## Prerequisites
 
@@ -26,7 +45,7 @@ Find out the (programming language, application framework, hosting) tuple of the
 
 ### Prefer auto-instrument if possible
 
-If the app is a C# ASP.NET Core app hosted in Azure App Service, use [AUTO guide](references/AUTO.md) to help user auto-instrument the app.
+If the app is a C# ASP.NET Core app hosted in Azure App Service, use [AUTO guide](references/auto.md) to help user auto-instrument the app.
 
 ### Manually instrument
 
@@ -43,6 +62,11 @@ No matter which option you choose, recommend the user to create the App Insights
 
 #### Modify application code
 
-- If the app is an ASP.NET Core app, see [ASPNETCORE guide](references/ASPNETCORE.md) for how to modify the C# code.
-- If the app is a Node.js app, see [NODEJS guide](references/NODEJS.md) for how to modify the JavaScript/TypeScript code.
-- If the app is a Python app, see [PYTHON guide](references/PYTHON.md) for how to modify the Python code.
+- If the app is an ASP.NET Core app, see [ASPNETCORE guide](references/aspnetcore.md) for how to modify the C# code.
+- If the app is a Node.js app, see [NODEJS guide](references/nodejs.md) for how to modify the JavaScript/TypeScript code.
+- If the app is a Python app, see [PYTHON guide](references/python.md) for how to modify the Python code.
+
+## SDK Quick References
+
+- **OpenTelemetry Distro**: [Python](references/sdk/azure-monitor-opentelemetry-py.md) | [TypeScript](references/sdk/azure-monitor-opentelemetry-ts.md)
+- **OpenTelemetry Exporter**: [Python](references/sdk/azure-monitor-opentelemetry-exporter-py.md) | [Java](references/sdk/azure-monitor-opentelemetry-exporter-java.md)

plugins/azure/README.md

@@ -16,14 +16,14 @@ An ASP.NET Core app typically has a Program.cs file that "builds" the app. Find
 
 ## Configure App Insights connection string
 
-The App Insights resource has a connection string. Add the connection string as an environment variable of the running app. You can use Azure CLI to query the connection string of the App Insights resource. See [scripts/appinsights.ps1](scripts/appinsights.ps1) for what Azure CLI command to execute for querying the connection string.
+The App Insights resource has a connection string. Add the connection string as an environment variable of the running app. You can use Azure CLI to query the connection string of the App Insights resource. See [scripts/appinsights.ps1](../scripts/appinsights.ps1) for what Azure CLI command to execute for querying the connection string.
 
 After getting the connection string, set this environment variable with its value.
 
 ```
 "APPLICATIONINSIGHTS_CONNECTION_STRING={your_application_insights_connection_string}"
 ```
 
-If the app has IaC template such as Bicep or terraform files representing its cloud instance, this environment variable should be added to the IaC template to be applied in each deployment. Otherwise, use Azure CLI to manually apply the environment variable to the cloud instance of the app. See [scripts/appinsights.ps1](scripts/appinsights.ps1) for what Azure CLI command to execute for setting this environment variable.
+If the app has IaC template such as Bicep or terraform files representing its cloud instance, this environment variable should be added to the IaC template to be applied in each deployment. Otherwise, use Azure CLI to manually apply the environment variable to the cloud instance of the app. See [scripts/appinsights.ps1](../scripts/appinsights.ps1) for what Azure CLI command to execute for setting this environment variable.
 
 > Important: Don't modify appsettings.json. It was a deprecated way to configure App Insights. The environment variable is the new recommended way.

skills/appinsights-instrumentation/SKILL.md

@@ -0,0 +1,31 @@
+# Azure Monitor OpenTelemetry Exporter — Java SDK Quick Reference
+
+> Condensed from **azure-monitor-opentelemetry-exporter-java**. Full patterns
+> (trace/metric/log export, spans, semantic conventions)
+> in the **azure-monitor-opentelemetry-exporter-java** plugin skill if installed.
+
+## Install
+```xml
+<dependency>
+    <groupId>com.azure</groupId>
+    <artifactId>azure-monitor-opentelemetry-exporter</artifactId>
+    <version>1.0.0-beta.x</version>
+</dependency>
+```
+
+> **DEPRECATED**: Migrate to `azure-monitor-opentelemetry-autoconfigure`.
+
+## Quick Start
+```java
+// Prefer autoconfigure instead:
+// <artifactId>azure-monitor-opentelemetry-autoconfigure</artifactId>
+```
+
+## Best Practices
+- Use autoconfigure — migrate to `azure-monitor-opentelemetry-autoconfigure`
+- Set meaningful span names — use descriptive operation names
+- Add relevant attributes — include contextual data for debugging
+- Handle exceptions — always record exceptions on spans
+- Use semantic conventions — follow OpenTelemetry semantic conventions
+- End spans in finally — ensure spans are always ended
+- Use try-with-resources — scope management with try-with-resources pattern

skills/appinsights-instrumentation/references/ASPNETCORE.md

@@ -0,0 +1,22 @@
+# Azure Monitor OpenTelemetry Exporter — Python SDK Quick Reference
+
+> Condensed from **azure-monitor-opentelemetry-exporter-py**. Full patterns
+> (metric exporter, log exporter, offline storage, sovereign clouds)
+> in the **azure-monitor-opentelemetry-exporter-py** plugin skill if installed.
+
+## Install
+pip install azure-monitor-opentelemetry-exporter
+
+## Quick Start
+```python
+from azure.monitor.opentelemetry.exporter import AzureMonitorTraceExporter
+exporter = AzureMonitorTraceExporter()  # reads APPLICATIONINSIGHTS_CONNECTION_STRING
+```
+
+## Best Practices
+- Use BatchSpanProcessor for production (not SimpleSpanProcessor)
+- Use ApplicationInsightsSampler for consistent sampling across services
+- Enable offline storage for reliability in production
+- Use AAD authentication instead of instrumentation keys
+- Set export intervals appropriate for your workload
+- Use the distro (azure-monitor-opentelemetry) unless you need custom pipelines