Azure DevOps MCP Server

What is Azure DevOps MCP Server?

This project implements a Model Context Protocol (MCP) server that enables AI assistants to interact with Azure DevOps for creating and updating tickets (work items). It acts as a bridge between LLMs and the Azure DevOps REST API, providing a standardized way for AI agents to manage work items.

How to use Azure DevOps MCP Server?

Install dependencies with pip install -r requirements.txt, create a .env file with your Azure DevOps PAT, organization URL, and default project, then run the server using mcp dev main.py, mcp install main.py --name "Azure DevOps Ticket Manager", or python main.py. To configure with Claude Desktop, add the server definition to your Claude Desktop configuration JSON.

Key features of Azure DevOps MCP Server

• Create new work items (tickets) in Azure DevOps
• Update existing work items with new fields
• Add comments to work items
• Retrieve work item details by ID
• Supports multiple work item types (Bug, Task, User Story)
• Optional parameters for assignment, state, priority, area, iteration, and tags

Use cases of Azure DevOps MCP Server

• Create a bug with a title and assign it to a team member
• Update a work item’s status to “Resolved” and add a comment
• Retrieve details of a specific work item by its ID
• Create a new user story for implementing a feature like two-factor authentication

FAQ from Azure DevOps MCP Server

What are the prerequisites for using Azure DevOps MCP Server?

Python 3.10+, an Azure DevOps account with appropriate permissions, and a Personal Access Token (PAT) with necessary scopes for the Azure DevOps API.

How do I configure Azure DevOps MCP Server with Claude Desktop?

Add a JSON entry to your Claude Desktop configuration file under mcpServers, specifying the command (python), the path to main.py, and the required environment variables (AZURE_DEVOPS_PAT, AZURE_DEVOPS_ORGANIZATION_URL, AZURE_DEVOPS_DEFAULT_PROJECT).

What tools does Azure DevOps MCP Server provide?

It provides four tools: create_work_item, update_work_item, add_work_item_comment, and get_work_item. Each accepts parameters like project, work item type, title, description, assigned_to, state, priority, area_path, iteration_path, and tags.

What security considerations should I be aware of?

The server requires a Personal Access Token (PAT) with appropriate permissions. Store your PAT securely and never commit it to version control. Run the server in a secure environment to prevent unauthorized access to your Azure DevOps resources.

What is the Model Context Protocol (MCP)?

MCP is an open standard that standardizes how applications provide context to Large Language Models (LLMs), creating a common interface for LLMs to interact with external tools and services without needing custom integrations.