Back to Catalog
Azure DevOps MCP Server logo
mcp-server2

Azure DevOps MCP Server

Official Microsoft MCP server that securely connects AI assistants like GitHub Copilot to your Azure DevOps organization, providing real-time context for work items, pull requests, pipelines, and more—running locally to keep your data secure.

Overview

The Azure DevOps MCP Server is Microsoft's official implementation of the Model Context Protocol (MCP) for Azure DevOps. It acts as a secure bridge between AI assistants (such as GitHub Copilot in Visual Studio Code and Visual Studio) and your Azure DevOps organization, injecting rich, real-time project context directly into AI prompts.

Unlike external cloud solutions, the local MCP Server runs in your environment, ensuring sensitive data never leaves your network. A remote hosted version is also available in public preview for easier setup with tools that support only remote MCP servers.

Key Features

  • Secure Data Access: Retrieve work items, pull requests, builds, releases, test plans, wikis, and repository information.
  • Local Execution: Runs on your machine using Node.js, keeping all data within your secure perimeter.
  • Remote Option: Hosted Azure DevOps endpoint with streamable HTTP transport (public preview).
  • AI Integration: Designed for seamless use with GitHub Copilot and other MCP-compatible AI assistants.
  • Comprehensive Tooling: Supports querying organization structure, teams, pipelines, and more.
  • Easy Configuration: Simple setup via npm and configuration files for VS Code or Visual Studio.

Use Cases

  • AI-Powered Development: Ask Copilot to summarize a work item, review a pull request, or suggest code changes based on your Azure DevOps context.
  • Automated Workflows: Enable agents to create or update work items, check build status, or analyze test results without switching tools.
  • Context-Aware Assistance: Get relevant answers tailored to your specific projects, sprints, and team structures.
  • Enterprise Security: Maintain compliance by avoiding external data sharing while leveraging advanced AI capabilities.

Installation and Setup

Prerequisites: Node.js 20+ and an Azure DevOps organization.

  1. Install globally: npm install -g @azure-devops/mcp
  2. Configure MCP settings in your IDE (VS Code or Visual Studio) with your organization name and authentication.
  3. Connect your AI assistant to the MCP server via stdio or the remote endpoint.

For detailed instructions, including remote server setup, refer to the Microsoft Learn documentation.

Remote MCP Server (Public Preview)

Microsoft also provides a hosted remote Azure DevOps MCP Server that eliminates local installation. It offers the same capabilities and is ideal for services that require remote HTTP transport.

Resources

  • Official GitHub Repository: https://github.com/microsoft/azure-devops-mcp
  • Microsoft Learn Overview: https://learn.microsoft.com/en-us/azure/devops/mcp-server/mcp-server-overview
  • Dev Blog Announcement: https://devblogs.microsoft.com/devops/azure-devops-mcp-server-public-preview/

The Azure DevOps MCP Server empowers developers to bring the full power of Azure DevOps into their AI workflows while maintaining enterprise-grade security and control.

Tags

azure-devopsmcpmcp-servertypescriptgithub-copilotai-assistantdevopswork-itemspull-requestspipelines