Microsoft Launches Azure DevOps MCP Server in Public Preview

Write for InfoQ

Microsoft has released the Azure DevOps Model Context Provider (MCP) Server in public preview.

The release enables GitHub Copilot to access and interact with Azure DevOps project data using natural language prompts within developer environments such as VS Code.

The MCP Server acts as a local bridge between GitHub Copilot in Agent Mode and a developer’s Azure DevOps instance. It makes structured project data such as work items, pull requests, test plans, builds, and wiki entries available as context for the AI assistant. This allows developers to query, create and update project information conversationally without leaving their IDE. According to Microsoft product manager Dan Hellem, “This lets the assistant give better, more accurate, and more relevant answers tailored to your specific Azure DevOps project.”

The MCP Server runs locally, which ensures that project data does not leave the developer’s network. It is installed as a Node.js service and integrates with Copilot through a configuration file and Azure CLI authentication.

This initial version provides functionality for core components within Azure DevOps. Developers can list projects, repositories, builds, releases, test plans, teams and iterations. Work items can be created and edited through natural language, with Copilot able to suggest the content automatically. Test cases and pull requests can also be generated and linked to backlog items. In a LinkedIn post, Lyon Till, senior software engineer at Microsoft, described the experience as “No more context switching - manage your entire DevOps workflow without leaving VS Code or Visual Studio.”

To get started, developers install the MCP Server from the official GitHub repository, sign in using the Azure CLI, configure their local mcp.json file and start the service. Once running, Copilot Agent Mode can handle commands such as “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.

The preview release is currently limited to Azure DevOps Services. On-premises Azure DevOps Server is not supported. Microsoft is inviting early adopters to share feedback and feature requests via GitHub Issues.

A separate MCP Server for Azure resource queries was launched in May, allowing developers to retrieve information about services such as Key Vault, Cosmos DB and Storage Accounts using natural language. The Azure DevOps MCP Server builds on the 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 licences.

Related Topics:

• Development
• DevOps
• AI, ML & Data Engineering
• Model Context Protocol (MCP)
• Continuous Integration
• Software Supply Chain
• Continuous Delivery

We protect your privacy.