Azure DevOps MCP server for AI agents

The MCP Azure DevOps Server provides a bridge that allows AI assistants like Claude to interact with Azure DevOps services through natural language requests, enabling management of work items, projects, teams, and more without needing to directly use the Azure DevOps interface.

Features

Work Item Management

Query work items using natural language
View complete work item information
Create new work items (tasks, bugs, user stories)
Update existing work items
Add and view comments on work items
Establish parent-child relationships between work items

Project Management

View all accessible projects in the organization
List all teams within the organization
Access team membership information
Retrieve area paths assigned to teams
Access team iteration/sprint configurations

Prerequisites

Python 3.10+
Azure DevOps account with appropriate permissions
Personal Access Token (PAT) with necessary scopes for Azure DevOps API access

Installation

You can install the MCP Azure DevOps server using pip:

# Install from PyPi
pip install mcp-azure-devops

Alternatively, you can clone and install from the repository:

# Clone the repository
git clone https://github.com/Vortiago/mcp-azure-devops.git
cd mcp-azure-devops

# Install in development mode
uv pip install -e ".[dev]"

Configuration

Create a .env file in the project root with the following variables:

AZURE_DEVOPS_PAT=your_personal_access_token
AZURE_DEVOPS_ORGANIZATION_URL=https://your-organization.visualstudio.com

Make sure to provide the full URL to your Azure DevOps organization. This can be either https://your-organization.visualstudio.com or https://dev.azure.com/your-organisation.

Running the Server

You can run the server in development mode with the MCP Inspector:

mcp dev src/mcp_azure_devops/server.py

To install it in Claude Desktop:

mcp install src/mcp_azure_devops/server.py --name "Azure DevOps Assistant"

Usage Examples

Once the server is running, you can interact with Azure DevOps through natural language commands. Here are some examples:

Querying Work Items

You can ask questions like:

Show me all active bugs assigned to me in the current sprint

Creating Work Items

To create a new work item:

Create a user story in the ProjectX with the title "Implement user authentication" and assign it to [email protected]

Updating Work Items

To modify an existing work item:

Change the status of bug #1234 to "Resolved" and add a comment explaining the fix

Team Management

To view team information:

Show me all the team members in the "Core Development" team in the "ProjectX" project

Viewing Project Structure

To explore your organization:

List all projects in my organization and show me the iterations for the Development team

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-azure-devops" '{"command":"python","args":["-m","mcp_azure_devops.server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mcp-azure-devops": {
            "command": "python",
            "args": [
                "-m",
                "mcp_azure_devops.server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-azure-devops": {
            "command": "python",
            "args": [
                "-m",
                "mcp_azure_devops.server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect