mcp-server-azure-devops

MCP.Pizza Chef: Tiberriver256

Work items, projects, repositories, branches, pull requests, and build runs are all reachable in conversation — you can list them, create them, and update them. One caveat the project raises itself: Microsoft now publishes an official server at microsoft/azure-devops-mcp, and cloud users are told to start there. This community version stays the better fit for on-premises Azure DevOps Server. It was still being updated in July 2026, and you sign in with the Azure command line or a personal access key.

Coding
Data

Use This MCP server To

List the work items assigned to me this sprint Create a bug with a description and assign it to someone Open a pull request and add reviewers Check which builds failed overnight Read a file from a repository without leaving the chat Update the status of a ticket I just finished

README

Azure DevOps MCP Server

A Model Context Protocol (MCP) server implementation for Azure DevOps, allowing AI assistants to interact with Azure DevOps APIs through a standardized protocol.

Looking for the official server? Microsoft maintains a product-supported Azure DevOps MCP at microsoft/azure-devops-mcp. If you use Azure DevOps Services (cloud), start there.

This community server remains a good fit when you need Azure DevOps Server (on-premises) support — especially older versions that may not work with Microsoft's MCP — or features not yet available in the official server. See Discussion #237 for more context.

Overview

This server implements the Model Context Protocol (MCP) for Azure DevOps, enabling AI assistants like Claude to interact with Azure DevOps resources securely. The server acts as a bridge between AI models and Azure DevOps APIs, providing a standardized way to:

  • Access and manage projects, work items, repositories, and more
  • Create and update work items, branches, and pull requests
  • Execute common DevOps workflows through natural language
  • Access repository content via standardized resource URIs
  • Safely authenticate and interact with Azure DevOps resources

Server Structure

The server is structured around the Model Context Protocol (MCP) for communicating with AI assistants. It provides tools for interacting with Azure DevOps resources including:

  • Projects
  • Work Items
  • Repositories
  • Pull Requests
  • Branches
  • Pipelines

Core Components

  • AzureDevOpsServer: Main server class that initializes the MCP server and registers tools
  • Feature Modules: Organized by feature area (work-items, projects, repositories, etc.)
  • Request Handlers: Each feature module provides request identification and handling functions
  • Tool Handlers: Modular functions for each Azure DevOps operation
  • Configuration: Environment-based configuration for organization URL, PAT, etc.

The server uses a feature-based architecture where each feature area (like work-items, projects, repositories) is encapsulated in its own module. This makes the codebase more maintainable and easier to extend with new features.

Getting Started

mcp-server-azure-devops FAQ

Is this the one I should install?
Read this first. The project itself says Microsoft now maintains an official, product-supported server at microsoft/azure-devops-mcp, and that people on Azure DevOps Services in the cloud should start there. This community version is recommended for on-premises Azure DevOps Server, including older versions the official one may not handle. It is still maintained, with changes as recent as July 2026.
Do I need a paid key?
No paid key, but you do need to prove who you are: either sign in with the Azure command line first, or generate a personal access key inside Azure DevOps and paste it into the configuration.
Which apps does it work in?
Claude Desktop and Cursor are documented, and it works with other assistants that support MCP servers.
Can I use this to triage my team's tickets?
Yes — you can search work items, read them, create new ones, and change their details, all by describing what you want.
Does it work with an on-premises server?
Yes, and that is now its main reason to exist. On-premises setups must use a personal access key rather than the Azure sign-in options.
How hard is setup?
Moderate. You paste a short block into your assistant's settings with your organization address, how you want to sign in, and a default project name. No downloading or building required.