Microsoft Unveils Azure DevOps MCP Server for GitHub Copilot Integration
Microsoft has launched the Azure DevOps Model Context Provider Server in public preview, enabling GitHub Copilot to interact with Azure DevOps project data using natural language prompts.
Microsoft has released the Azure DevOps Model Context Provider (MCP) Server in public preview, marking a significant step in integrating GitHub Copilot with Azure DevOps. This tool allows developers to interact with project data using natural language prompts within their development environments, such as VS Code.
Key Features of the MCP Server
The MCP Server acts as a local bridge between GitHub Copilot in Agent Mode and a developer’s Azure DevOps instance. It provides structured project data—including work items, pull requests, test plans, builds, and wiki entries—as context for the AI assistant. According to Microsoft product manager Dan Hellem, this enables Copilot to deliver "better, more accurate, and more relevant answers tailored to your specific Azure DevOps project."
- Local Execution: The MCP Server runs locally, ensuring project data remains within the developer’s network.
- Node.js Service: Installed as a Node.js service, it integrates with Copilot via a configuration file and Azure CLI authentication.
- Core Functionality: Developers can list projects, repositories, builds, releases, test plans, teams, and iterations. They can also create and edit work items, test cases, and pull requests through natural language commands.
Developer Experience
Lyon Till, Senior Software Engineer at Microsoft, praised the tool in a LinkedIn post, stating, "No more context switching - manage your entire DevOps workflow without leaving VS Code or Visual Studio."
Getting Started
To use the MCP Server, developers must:
- Install it from the official GitHub repository.
- Sign in using the Azure CLI.
- Configure their local
mcp.jsonfile. - Start the service.
Once running, Copilot Agent Mode can handle commands like "list work items assigned to me" or "create a user story for login failure handling," translating these into authenticated REST API calls to Azure DevOps.
Limitations and Feedback
The preview release is currently limited to Azure DevOps Services and does not support on-premises Azure DevOps Server. Microsoft encourages early adopters to share feedback and feature requests via GitHub Issues.
Broader Context
This release follows the launch of a separate MCP Server for Azure resource queries in May, which allowed developers to retrieve information about services like Key Vault, Cosmos DB, and Storage Accounts using natural language. The Azure DevOps MCP Server builds on this same underlying approach.
Documentation, setup guidance, and source code are available on GitHub. The preview is open to developers using Azure DevOps Services and GitHub Copilot Business or Enterprise licenses.
About the Author
Mark Silvester is a technology journalist covering Microsoft and DevOps innovations.
Related News
GitHub CEO Thomas Dohmke departs amid rising AI coding competition
Microsoft's GitHub CEO Thomas Dohmke is stepping down as the company faces increasing competition from AI coding startups like Cursor and Replit.
Elon Musk's xAI Files Trademark for Macrohard AI Software Company
Elon Musk's xAI has filed a trademark for the name Macrohard, signaling plans to launch a new AI-based software company. The move follows Musk's hints about creating a multi-agent AI software firm.
About the Author
Dr. Sarah Chen
AI Research Expert
A seasoned AI expert with 15 years of research experience, formerly worked at Stanford AI Lab for 8 years, specializing in machine learning and natural language processing. Currently serves as technical advisor for multiple AI companies and regularly contributes AI technology analysis articles to authoritative media like MIT Technology Review.