Azure
Enables monitoring and management of Azure resources including Virtual Machines (VMs) and Virtual Machine Scale Sets (VMSS) through a RESTful API with secure Service Principal authentication.
What is Azure?
Azure is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables monitoring and management of azure resources including virtual machines (vms) and virtual machine scale sets (vmss) through a restful api with secure service principal authentication.
Enables monitoring and management of Azure resources including Virtual Machines (VMs) and Virtual Machine Scale Sets (VMSS) through a RESTful API with secure Service Principal authentication.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables monitoring and management of Azure resources includi
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx azure-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Azure
The Azure MCP Server exposes over 43 Azure services through the Model Context Protocol, enabling AI assistants to monitor and manage Azure infrastructure using natural language. It covers Virtual Machines, Storage, Cosmos DB, SQL databases, Key Vault, AKS, App Service, Azure AI Search, and many more services, all secured through Azure's standard authentication mechanisms including Service Principal and Azure CLI credentials. Developers and DevOps teams can use it to query resources, manage deployments, and automate Azure operations directly from Claude or other MCP-compatible clients.
Prerequisites
- Azure subscription with appropriate permissions on the resources you want to manage
- Azure CLI installed and configured, or a Service Principal with AZURE_TENANT_ID, AZURE_CLIENT_ID, and AZURE_CLIENT_SECRET
- Node.js 18+ (for npm/npx install) or .NET SDK (for dotnet tool install) or Python with pipx
- An MCP-compatible client such as Claude Desktop, Claude Code, or Cursor
Install the Azure MCP Server
Install using your preferred runtime. The npm package is the most common choice and works on all platforms. The .NET tool and Python package are also available.
# npm (recommended)
npm install -g @azure/mcp@latest
# .NET
dotnet tool install Azure.Mcp
# Python
pipx install msmcp-azureAuthenticate with Azure
Log in with the Azure CLI for local development. The server will use your CLI credentials automatically. For production or CI environments, set the Service Principal environment variables instead.
# Option 1: Azure CLI (easiest for local dev)
az login
# Option 2: Service Principal environment variables
export AZURE_TENANT_ID="your-tenant-id"
export AZURE_CLIENT_ID="your-client-id"
export AZURE_CLIENT_SECRET="your-client-secret"Test the server manually
Run the server directly to verify it starts without errors. It will output MCP protocol messages over stdio.
npx -y @azure/mcp@latest server startConfigure the MCP client
Add the Azure MCP server to your claude_desktop_config.json. For Service Principal authentication, include the credentials as environment variables in the config.
{
"mcpServers": {
"azure": {
"command": "npx",
"args": ["-y", "@azure/mcp@latest", "server", "start"],
"env": {
"AZURE_TENANT_ID": "your-tenant-id",
"AZURE_CLIENT_ID": "your-client-id",
"AZURE_CLIENT_SECRET": "your-client-secret"
}
}
}
}Optionally restrict to specific services
If you use VS Code with the Azure MCP extension, you can restrict which services are exposed using the azureMcp.enabledServices setting. You can also enable read-only mode to prevent write operations.
{
"azureMcp.serverMode": "namespace",
"azureMcp.enabledServices": ["storage", "keyvault", "compute"],
"azureMcp.readOnly": true
}Azure Examples
Client configuration
Full claude_desktop_config.json entry for the Azure MCP server using npx with Service Principal credentials.
{
"mcpServers": {
"azure": {
"command": "npx",
"args": ["-y", "@azure/mcp@latest", "server", "start"],
"env": {
"AZURE_TENANT_ID": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"AZURE_CLIENT_ID": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
"AZURE_CLIENT_SECRET": "your-client-secret"
}
}
}
}Prompts to try
These prompts work with the Azure MCP server once it is authenticated and connected to your subscription.
- "List all my Azure storage containers in the 'production' resource group"
- "What virtual machines are running in my subscription and what are their sizes?"
- "Create a new RSA key called 'app-encryption-key' in key vault 'my-vault'"
- "Show me the web apps in my 'my-resource-group' resource group and their deployment slots"
- "Check Azure Advisor recommendations for cost savings in my subscription"Troubleshooting Azure
Authentication errors when the server starts
Ensure you are logged in with 'az login' and the correct subscription is active ('az account show'). For Service Principal auth, verify all three environment variables (AZURE_TENANT_ID, AZURE_CLIENT_ID, AZURE_CLIENT_SECRET) are set correctly and the principal has the necessary role assignments on target resources.
Server starts but no Azure tools appear in the client
Restart the MCP client after updating the config file. Verify the npx command resolves correctly by running 'npx -y @azure/mcp@latest server start' in a terminal. If using serverMode 'namespace' or 'single', ensure the target service namespace is valid.
Operations fail for specific Azure services
The Service Principal or user account may lack the required RBAC role for that service. Assign the appropriate built-in role (e.g., 'Storage Blob Data Contributor' for blob operations, 'Key Vault Secrets User' for Key Vault reads) in the Azure portal under Access Control (IAM) for the target resource.
Frequently Asked Questions about Azure
What is Azure?
Azure is a Model Context Protocol (MCP) server that enables monitoring and management of azure resources including virtual machines (vms) and virtual machine scale sets (vmss) through a restful api with secure service principal authentication. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Azure?
Follow the installation instructions on the Azure GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Azure?
Azure works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Azure free to use?
Yes, Azure is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Azure Alternatives — Similar Cloud Services Servers
Looking for alternatives to Azure? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Azure in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Azure?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.