Azure MCPサーバー

Azure MCP Server

[!NOTE] Azure MCP Server 2.0 is now generally available.

All Azure MCP tools in a single server. The Azure MCP Server implements the MCP specification to create a seamless connection between AI agents and Azure services. Azure MCP Server can be used alone or with the GitHub Copilot for Azure extension in VS Code.

Table of Contents

• Overview
• Local Setup
  • Developer Tools
    • VS Code (Recommended)
    • Visual Studio 2026
    • Visual Studio 2022
    • IntelliJ IDEA
    • Eclipse IDE
    • Google Antigravity
    • Claude Code
    • Manual Setup
    • GitHub Copilot CLI Configuration
    • GitHub Copilot SDK Configuration
  • Package Manager
    • NuGet
    • NPM
    • PyPI
    • Docker
    • MCPB
• Remote Setup
• Usage
  • Getting Started
  • Sovereign Cloud Support
  • What can you do with the Azure MCP Server?
  • Complete List of Supported Azure Services
• Support and Reference
  • Documentation
  • Feedback and Support
  • Security
  • Permissions and Risk
  • Data Collection
  • Compliance Responsibility
  • Third Party Components
  • Export Control
  • No Warranty / Limitation of Liability
  • Contributing
  • Code of Conduct

Overview

Azure MCP Server supercharges your agents with Azure context across numerous Azure services.

Local Setup

Install Azure MCP Server using either an IDE extension or package manager. Choose one method below.

[!IMPORTANT] Authenticate to Azure before running the Azure MCP server. See the Authentication guide for authentication methods and instructions.

Developer Tools

Start using Azure MCP with your favorite IDE. We recommend VS Code:

VS Code (Recommended)

Compatible with both the Stable and Insiders builds of VS Code.

1. Install the GitHub Copilot Chat extension.
2. Install the Azure MCP Server extension.
3. Sign in to Azure (Command Palette: Azure: Sign In).

Visual Studio 2026

1. Download Visual Studio 2026 or Visual Studio 2026 Insiders and install using the Visual Studio Installer.
   • If Visual Studio 2026 is already installed, open the Visual Studio Installer and select the Modify button, which displays the available workloads.
2. On the Workloads tab, select Azure and AI development and select GitHub Copilot.
3. Click install while downloading to complete the installation.

For more information, visit Install GitHub Copilot for Azure in Visual Studio 2026

Visual Studio 2022

From within Visual Studio 2022 install GitHub Copilot for Azure (VS 2022):

1. Go to Extensions | Manage Extensions...
2. Switch to the Browse tab in Extension Manager
3. Search for Github Copilot for Azure
4. Click Install

IntelliJ IDEA

1. Install either the IntelliJ IDEA Ultimate or IntelliJ IDEA Community edition.
2. Install the GitHub Copilot plugin.
3. Install the Azure Toolkit for Intellij plugin.

Eclipse IDE

1. Install Eclipse IDE.
2. Install the GitHub Copilot plugin.
3. Install the Azure Toolkit for Eclipse plugin.

Google Antigravity

1. Install and open Google Antigravity.

2. In the editor's agent side panel, select ... > MCP Servers > Manage MCP Servers > View raw config.

3. Add Azure MCP Server to the mcpServers object in mcp_config.json:

   {
       "mcpServers": {
           "azure-mcp-server": {
               "command": "npx",
               "args": ["-y", "@azure/mcp@latest", "server", "start"]
           }
       }
   }
   

Antigravity stores global configuration at ~/.gemini/config/mcp_config.json. For workspace-only configuration, use .agents/mcp_config.json. For more information, see the Google Antigravity MCP documentation.

Claude Code

The Azure plugin packages the Azure MCP Server along with Azure-related agents and skills, bringing Azure integration to Claude Code in one installation.

1. Install Claude Code.
2. Install the Azure plugin from Anthropic's official plugin marketplace by running the following command in Claude Code:

   /plugin install azure@claude-plugins-official
   

For more information on discovering and installing plugins, see the Claude Code plugins documentation.

Manual Setup

Azure MCP Server can also be configured across other IDEs, CLIs, and MCP clients:

Use one of the following options to configure your mcp.json:

Option 1: Configure using .NET tool (dnx)

• To use Azure MCP server from .NET, you must have the latest .NET 10 SDK LTS installed. .NET 10 and later adds a command, dnx, which is used to download, install, and run the MCP server from nuget.org. To verify the .NET version, run the following command in the terminal: dotnet --info

• Configure the mcp.json file with the following:

  {
      "mcpServers": {
          "azure-mcp-server": {
              "command": "dnx",
              "args": [
                  "Azure.Mcp",
                  "--source",
                  "https://api.nuget.org/v3/index.json",
                  "--yes",
                  "--",
                  "azmcp",
                  "server",
                  "start"
              ],
              "type": "stdio"
          }
      }
  }
  

Option 2: Configure using Node.js (npm/npx)

• To use Azure MCP server from node one must have Node.js (LTS) installed and available on your system PATH — this provides both npm and npx. We recommend the latest Node.js LTS version. To verify your installation run: node --version, npm --version, and npx --version.

• Configure the mcp.json file with the following:

  {
      "mcpServers": {
          "azure-mcp-server": {
          "command": "npx",
          "args": [
              "-y",
              "@azure/mcp@latest",
              "server",
              "start"
              ]
          }
      }
  }
  

Option 3: Configure using Python (uvx)

• To use Azure MCP server from Python, you must have uv installed. uv is a fast Python package installer and resolver. To verify your installation run: uv --version and uvx --version.

• Configure the mcp.json file with the following:

  {
      "mcpServers": {
          "azure-mcp-server": {
              "command": "uvx",
              "args": [
                  "--from",
                  "msmcp-azure",
                  "azmcp",
                  "server",
                  "start"
              ]
          }
      }
  }
  

Note: When manually configuring Visual Studio and Visual Studio Code, use servers instead of mcpServers as the root object.

Client-Specific Configuration

IDE	File Location	Documentation Link
VS Code	.vscode/mcp.json (workspace)settings.json (user)	VS Code MCP Documentation
Visual Studio	.mcp.json (solution/workspace)	Visual Studio MCP Setup
GitHub Copilot CLI	~/.copilot/mcp-config.json	Copilot CLI MCP Configuration
Claude Code	~/.claude.json or .mcp.json (project)	Claude Code MCP Configuration
Eclipse IDE	GitHub Copilot Chat -> Configure Tools -> MCP Servers	Eclipse MCP Documentation
IntelliJ IDEA	Built-in MCP server (2025.2+)Settings > Tools > MCP Server	IntelliJ MCP Documentation
Google Antigravity	~/.gemini/config/mcp_config.json (global).agents/mcp_config.json (workspace)	Google Antigravity MCP Documentation
Cursor	~/.cursor/mcp.json or .cursor/mcp.json	Cursor MCP Documentation
Windsurf	~/.codeium/windsurf/mcp_config.json	Windsurf Cascade MCP Integration
Amazon Q Developer	~/.aws/amazonq/mcp.json (global).amazonq/mcp.json (workspace)	AWS Q Developer MCP Guide
Claude Desktop	~/.claude/claude_desktop_config.json (macOS)%APPDATA%\Claude\claude_desktop_config.json (Windows)	Claude Desktop MCP Setup

GitHub Copilot CLI Configuration

GitHub Copilot CLI supports MCP servers via the /mcp command.

Add Azure MCP Server

1. In a Copilot CLI session, run /mcp add to open the MCP server configuration form.

2. Fill in the fields:

   Field	Value
   Server Name	azure-mcp
   Server Type	1 (Local)
   Command	npx -y @azure/mcp@latest server start
   Environment Variables	(leave blank - uses Azure CLI auth)
   Tools	*

   Alternative Command (using .NET): dotnet dnx Azure.Mcp server start

3. Press Ctrl+S (or Cmd+S on macOS) to save the server configuration.

Verification

Verify the MCP server is configured by running:

/mcp show

You should see output similar to:

● MCP Server Configuration:
  • azure-mcp (local): Command: npx

Total servers: 1
Config file: ~/.copilot/mcp-config.json

Managing MCP Servers

• List servers: /mcp show
• Remove a server: /mcp remove azure-mcp
• Get help: /mcp help

GitHub Copilot SDK Configuration

The GitHub Copilot SDK enables programmatic integration of Azure MCP tools into your applications across multiple languages.

Using GitHub Copilot SDK with Azure MCP

This guide explains how to configure the GitHub Copilot SDK to use Azure MCP (Model Context Protocol) tools for interacting with Azure resources.

Overview

Azure MCP provides a set of tools that enable AI assistants to interact with Azure resources directly. When integrated with the Copilot SDK, you can build applications that leverage natural language to manage Azure subscriptions, resource groups, storage accounts, and more.

Prerequisites

1. GitHub Copilot CLI - Install from GitHub Copilot CLI
2. Azure MCP Server - Available via npm: @azure/mcp
3. Azure CLI - Authenticated via az login
4. Valid GitHub Copilot subscription

Install Azure MCP Server

# Option 1: Use npx (downloads on demand)
npx -y @azure/mcp@latest server start

# Option 2: Install globally (faster startup)
npm install -g @azure/mcp@latest

---

Key Configuration Insight

Important: MCP servers must be configured in the session config for tools to be available. The critical configuration is:

{
  "mcp_servers": {
    "azure-mcp": {
      "type": "local",
      "command": "npx",
      "args": ["-y", "@azure/mcp@latest", "server", "start"],
      "tools": ["*"]
    }
  }
}

The tools: ["*"] parameter is essential - it enables all tools from the MCP server for the session.

---

Python

Installation

pip install github-copilot-sdk