The Azure MCP Server implements the MCP specification to create a seamless connection between AI agents and key Azure services like Azure Storage, Cosmos DB, and more.

Please note that this project is in Public Preview and implementation may significantly change prior to our General Availability.

The Azure MCP Server supercharges your agents with Azure context. Here are some cool prompts you can try:

• "List my Azure storage accounts"
• "Show me all my Cosmos DB databases"
• "What indexes do I have in my Azure AI Search service 'mysvc'?"
• "List my resource groups"
• "Show me the tables in my Storage account"
• "List containers in my Cosmos DB database"
• "Get details about my Storage container"
• "Get Kusto databases in cluster 'mycluster'"
• "Sample 10 rows from table 'StormEvents' in Kusto database 'db1'"

• "Query my Log Analytics workspace"
• "Let's search this index for 'my search query'"

• "List my App Configuration stores"
• "Show my key-value pairs in App Config"

• "List my Azure CDN endpoints"
• "Help me build an Azure application using Node.js"

The Azure MCP Server creates a seamless integration between AI agents and Azure services through:

• 🔄 Smart JSON communication that AI agents understand
• 🏗️ Natural language commands that get translated to Azure operations
• 💡 Intelligent parameter suggestions and auto-completion
• ⚡ Consistent error handling that makes sense

The Azure MCP Server provides tools for interacting with the following Azure services:

• List Azure AI Search services
• List indexes and look at their schema and configuration
• Query search indexes

• List Cosmos DB accounts
• List and query databases
• Manage containers and items
• Execute SQL queries against containers

• List and query databases.
• List and get schema for tables.
• List, get configuration and get parameters for servers.

• List Kusto clusters
• List databases in a Kusto cluster
• List tables in a Kusto database
• Get schema for a Kusto table
• Sample rows from a Kusto table
• Query Kusto databases using KQL

• List Storage accounts
• Manage blob containers and blobs
• List and query Storage tables
• Get container properties and metadata

• List Log Analytics workspaces
• Query logs using KQL
• List available tables
• Configure monitoring options

• List App Configuration stores
• Manage key-value pairs
• Handle labeled configurations
• Lock/unlock configuration settings

• List, create, and get keys

• List resource groups
• Resource group management operations

• Peek at messages from subscriptions and queues
• Examine properties and runtime information about queues, topics, and subscriptions

• Execute Azure CLI commands directly
• Support for all Azure CLI functionality
• JSON output formatting
• Cross-platform compatibility

• Execute Azure Developer CLI commands directly
• Support for template discovery, template initialization, provisioning and deployment
• Cross-platform compatibility

• Get secure, production-grade Azure SDK best practices for effective code generation.

For detailed command documentation and examples, see Azure MCP Commands.

The Azure MCP Server requires Node.js to install and run the server. If you don't have it installed, follow the instructions here.

The Azure MCP Server provides Azure SDK and Azure CLI developer tools. It can be used alone or with the GitHub Copilot for Azure extension in VS Code. If you're interested in broad developer support across a variety of Azure development scenarios not included in the Azure MCP Server, such as searching documentation on Microsoft Learn, we recommend this extension as well.

1. Install either the stable or Insiders release of VS Code:
   • 💫 Stable release
   • 🔮 Insiders release
2. Install the GitHub Copilot and GitHub Copilot Chat extensions
3. Install Node.js 20 or later
   • Ensure node and npm are in your path
4. Open VS Code in an empty folder

Click one of these buttons to install the Azure MCP Server for VS Code or VS Code Insiders.

Once you've installed the Azure MCP Server, make sure you select GitHub Copilot Agent Mode and refresh the tools list. To learn more about Agent Mode, visit the VS Code Documentation.

For a step-by-step installation, follow these instructions:

1. Add .vscode/mcp.json:

{
  "servers": {
    "Azure MCP Server": {
      "command": "npx",
      "args": [
        "-y",
        "@azure/mcp@latest",
        "server",
        "start"
      ]
    }
  }
}

For a step-by-step installation, follow these instructions:

1. Clone repository
2. From repository root, build Docker image: docker build -t azure/azuremcp .
3. Create an .env file with environment variables that match one of the EnvironmentCredential sets. For example, a .env file using a service principal could look like:

AZURE_TENANT_ID={YOUR_AZURE_TENANT_ID}
AZURE_CLIENT_ID={YOUR_AZURE_CLIENT_ID}
AZURE_CLIENT_SECRET={YOUR_AZURE_CLIENT_SECRET}

1. Add .vscode/mcp.json or update existing MCP configuration. Replace /full/path/to/.env with a path to your .env file.

{
  "servers": {
    "Azure MCP Server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "azure/azuremcp",
        "--env-file",
        "/full/path/to/.env"
      ]
    }
  }
}

Optionally, customers can use --env or --volume to pass authentication values.

1. Open GitHub Copilot in VS Code and switch to Agent mode
2. You should see the Azure MCP Server in the list of tools
3. Try a prompt that tells the agent to use the Azure MCP Server, such as "List my Azure Storage containers"
4. The agent should be able to use the Azure MCP Server tools to complete your query

You can easily configure your MCP client to use the Azure MCP Server. Have your client run the following command and access it via standard IO or SSE.

Configure the MCP client to execute: npx -y @azure/mcp@latest server start. For instructions on using VS Code, follow instructions in One-Click Install or Manual Install.

1. Open a terminal window and execute: npx -y @azure/mcp@latest server start --transport sse
2. The server starts up and is hosted at: http://localhost:5008. To use another port, append --port {YOUR-PORT-NUMBER}.
3. Open your MCP client and add the SSE configuration value. This may differ between MCP clients. In VS Code, it will look like:

   {
      "servers": {
        "Azure MCP Server": {
          "type": "sse",
          "url": "http://localhost:5008/sse"
        }
      }
    }

More end-to-end MCP client/agent guides are coming soon!

See Troubleshooting guide for help with common issues and logging.

The Azure MCP Server seamlessly integrates with your host operating system's authentication mechanisms, making it super easy to get started! We use Azure Identity under the hood via DefaultAzureCredential, which tries these credentials in order:

1. Environment Variables (EnvironmentCredential) - Perfect for CI/CD pipelines
2. Shared Token Cache (SharedTokenCacheCredential) - Uses cached tokens from other tools
3. Visual Studio (VisualStudioCredential) - Uses your Visual Studio credentials
4. Azure CLI (AzureCliCredential) - Uses your existing Azure CLI login
5. Azure PowerShell (AzurePowerShellCredential) - Uses your Az PowerShell login
6. Azure Developer CLI (AzureDeveloperCliCredential) - Uses your azd login
7. Interactive Browser (InteractiveBrowserCredential) - Falls back to browser-based login if needed

If you're already logged in through any of these methods, the Azure MCP Server will automatically use those credentials. Ensure that you have the correct authorization permissions in Azure (e.g. read access to your Storage account) via RBAC (Role-Based Access Control). To learn more about Azure's RBAC authorization system, visit this link.

If you're running into any issues with authentication, visit our troubleshooting guide.

By default, the Azure MCP Server excludes production credentials like Managed Identity and Workload Identity. To enable these credentials, set the environment variable:

AZURE_MCP_INCLUDE_PRODUCTION_CREDENTIALS=true

This is useful when running on Azure services where you want to use managed identities.

Your credentials are always handled securely through the official Azure Identity SDK - we never store or manage tokens directly.

MCP as a phenomenon is very novel and cutting-edge. As with all new technology standards, consider doing a security review to ensure any systems that integrate with MCP servers follow all regulations and standards your system is expected to adhere to. This includes not only the Azure MCP Server, but any MCP client/agent that you choose to implement down to the model provider.

We welcome contributions to the Azure MCP Server! Whether you're fixing bugs, adding new features, or improving documentation, your contributions are welcome.

Please read our Contributing Guide for guidelines on:

• 🛠️ Setting up your development environment
• ✨ Adding new commands
• 📝 Code style and testing requirements
• 🔄 Making pull requests

This project has adopted the Microsoft Open Source Code of Conduct. For more information, see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.