Azure DevOps MCP Server

What is Azure DevOps MCP Server?

Azure DevOps MCP Server is a bridge between AI models and Azure DevOps APIs, allowing large language models to interact with Azure DevOps projects, work items, repositories, pipelines, pull requests, and more. It exposes these capabilities as standardized MCP tools, supporting secure authentication and flexible integration into various AI platforms.

How to Configure

1. Install Node.js (v16+) and npm or yarn.
2. Ensure you have access to an Azure DevOps organization and the required authentication credentials (Personal Access Token, Azure Identity, or Azure CLI).
3. Integrate with your AI host (e.g., Claude Desktop, Cursor AI) by adding the MCP server config to your settings file. Example configuration:
   • For Azure Identity (using az login):

     {
       "mcpServers": {
         "azureDevOps": {
           "command": "npx",
           "args": ["-y", "@tiberriver256/mcp-server-azure-devops"],
           "env": {
             "AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/your-organization",
             "AZURE_DEVOPS_AUTH_METHOD": "azure-identity",
             "AZURE_DEVOPS_DEFAULT_PROJECT": "your-project-name"
           }
         }
       }
     }
     

   • For PAT authentication:

     {
       "mcpServers": {
         "azureDevOps": {
           "command": "npx",
           "args": ["-y", "@tiberriver256/mcp-server-azure-devops"],
           "env": {
             "AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/your-organization",
             "AZURE_DEVOPS_AUTH_METHOD": "pat",
             "AZURE_DEVOPS_PAT": "<YOUR_PAT>",
             "AZURE_DEVOPS_DEFAULT_PROJECT": "your-project-name"
           }
         }
       }
     }
     

4. For more environment variables and advanced authentication (service principals, CLI), refer to the official docs.

How to Use

• Start the Azure DevOps MCP Server using your configured settings, often through your AI assistant host (Claude Desktop, Cursor AI, etc.).
• Once running, AI models can discover and invoke available tools (functions) for DevOps-related actions, such as listing projects, creating work items, managing repositories, and triggering pipelines.
• Use natural language prompts to instruct your AI assistant; it will communicate through MCP to perform the desired operations in Azure DevOps.
• All actions are performed securely using your chosen authentication method, and results are returned to your assistant or workflow.

Key Features

• Standardized and extensible protocol for integrating Azure DevOps with AI assistants.
• Supports multiple authentication modes: Personal Access Token, Azure Identity, and Azure CLI.
• Modular structure organized by DevOps feature areas (projects, work items, repos, pipelines, etc.).
• Rich set of MCP tools for reading, searching, modifying, and automating DevOps tasks.
• Secure access to both cloud and (optionally) local resources, respecting user permissions.
• Easy configuration and integration with popular AI hosts and IDEs.

Use Cases

• Automating DevOps workflows and processes via AI-driven commands (e.g., creating and updating work items by prompt).
• Integrating Azure DevOps information and actions into LLM-powered chatbots or coding assistants.
• Enabling rapid code, work item, or documentation searches with natural language queries.
• Allowing AI agents to trigger builds, manage pull requests, or monitor pipeline runs.
• Enhancing productivity and DevOps visibility for engineering teams using conversational interfaces.

FAQ

Q1: Which authentication methods are supported?
A: The server supports Personal Access Token (PAT), Azure Identity (DefaultAzureCredential), and Azure CLI for authentication. Each method has specific setup steps; refer to the documentation for details.

Q2: Can I limit AI access to specific projects or repositories?
A: Yes, access is governed by the credentials and permissions provided. The AI assistant will only be able to access projects and resources available to the authenticated account.

Q3: What should I do if authentication fails or the server cannot connect to Azure DevOps?
A: Common troubleshooting steps include verifying credential validity, checking permission scopes, confirming network connectivity, and reviewing logs for misconfiguration errors. See the Authentication Guide for more troubleshooting tips.

Q4: How do I update or extend the set of available tools?
A: The server is modular. New tools or feature modules can be added by updating the codebase and registering new tool handlers; see the contributing guide for help.

Q5: Is it safe to run this server on my local machine?
A: Yes, provided you control the environment and secure your authentication credentials. The server does not expose services externally by default.