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.

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
• 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
• Tool Handlers: Modular functions for each Azure DevOps operation
• Configuration: Environment-based configuration for organization URL, PAT, etc.

Getting Started

Prerequisites

• Node.js (v16+)
• npm or yarn
• Azure DevOps account with appropriate access
• Authentication credentials (see Authentication Guide for details):
  • Personal Access Token (PAT), or
  • Azure Identity credentials, or
  • Azure CLI login

Installation

1. Clone the repository:
   git clone https://github.com/your-username/azure-devops-mcp.git cd azure-devops-mcp
2. Install dependencies:
   npm install
3. Set up your environment:Option A: Using the automated setup script (recommended):
   chmod +x setup_env.sh ./setup_env.sh
   This script will:
   • Check for and install the Azure CLI DevOps extension if needed
   • Let you select from your available Azure DevOps organizations
   • Optionally set a default project
   • Create a Personal Access Token with the required permissions
   • Generate your .env file with the correct settings

   Option B: Manual setup:

   cp .env.example .env

   Then edit the .env file with your Azure DevOps credentials (see Authentication section below).

Running the Server

Build the TypeScript files:

Start the server:

For development with hot reloading:

Authentication Methods

This server supports multiple authentication methods for connecting to Azure DevOps APIs. For detailed setup instructions, configuration examples, and troubleshooting tips, see the Authentication Guide.

Supported Authentication Methods

1. Personal Access Token (PAT) - Simple token-based authentication
2. Azure Identity (DefaultAzureCredential) - Flexible authentication using the Azure Identity SDK
3. Azure CLI - Authentication using your Azure CLI login

Example configuration files for each authentication method are available in the examples directory.

Environment Variables

For a complete list of environment variables and their descriptions, see the Authentication Guide.

Key environment variables include:

Troubleshooting Authentication

For detailed troubleshooting information for each authentication method, see the Authentication Guide.

Common issues include:

• Invalid or expired credentials
• Insufficient permissions
• Network connectivity problems
• Configuration errors

Authentication Implementation Details

For technical details about how authentication is implemented in the Azure DevOps MCP server, see the Authentication Guide and the source code in the src/auth directory.

Available Tools

The Azure DevOps MCP server provides a variety of tools for interacting with Azure DevOps resources. For detailed documentation on each tool, please refer to the corresponding documentation.

Core Navigation Tools

• list_organizations: List all accessible organizations
• list_projects: List all accessible projects
• list_repositories: List all repositories in a project

For comprehensive documentation on all core navigation tools, see the Core Navigation Tools Guide.

Project Tools

• get_project: Get details of a specific project

For project-specific tool documentation, see the Projects Tools Guide.

Repository Tools

• get_repository: Get repository details

For repository-specific tool documentation, see the Repositories Tools Guide.

Work Item Tools

• get_work_item: Retrieve a work item by ID
• create_work_item: Create a new work item

Testing

Unit Tests

Run unit tests with:

Integration Tests

Integration tests require a connection to a real Azure DevOps instance. To run them:

1. Ensure your .env file is configured with valid Azure DevOps credentials:
   AZURE_DEVOPS_ORG_URL=https://dev.azure.com/your-organization AZURE_DEVOPS_PAT=your-personal-access-token AZURE_DEVOPS_DEFAULT_PROJECT=your-project-name
2. Run the integration tests:
   npm run test:integration

CI Environment

For running tests in CI environments (like GitHub Actions), see CI Environment Setup for instructions on configuring secrets.

Development

This project follows Test-Driven Development practices. Each new feature should:

1. Begin with a failing test
2. Implement the minimal code to make the test pass
3. Refactor while keeping tests green

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.