Azure DevOps MCP Server

A Model Context Protocol (MCP) server that provides Azure DevOps integration for AI assistants like Claude, ChatGPT, and other MCP-compatible tools.

Features

• Work Item Management: Retrieve work items and backlog items from Azure DevOps
• Team Integration: Access team-specific backlogs and work items
• Flexible Querying: Support for custom fields, date filters, and expansion options

Available Tools

• list_backlog_work_items - Retrieve backlog work items for a project/team
• get_work_item - Get detailed information about a specific work item

Setup

1. Install dependencies:

   npm install

2. Configure environment:

   cp .env.example .env

   Edit .env with your Azure DevOps credentials:

   AZURE_DEVOPS_PAT=your_personal_access_token_here
   AZURE_DEVOPS_ORG_URL=https://dev.azure.com/your-org

3. Test the server:

   npm test
   npm run inspect

Integration with AI Assistants

Claude Desktop

Add this server to your Claude Desktop configuration file:

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

{
  "mcpServers": {
    "azdevops": {
      "command": "npx",
      "args": [
          "-y",
          "azdevops-mcp-alx"
        ],
      "env": {
        "AZURE_DEVOPS_PAT": "your_personal_access_token",
        "AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/your-org"
      }
    }
  }
}

ChatGPT (via OpenAI API)

For ChatGPT integration, you'll need to use a custom implementation or third-party bridge since ChatGPT doesn't natively support MCP. Consider using:

1. OpenAI GPT with Function Calling: Convert MCP tools to OpenAI function definitions
2. Custom Proxy: Build a REST API wrapper around this MCP server
3. Third-party MCP Bridges: Use tools like mcp-to-openai adapters

Example function definition for OpenAI:

{
  "name": "get_work_item",
  "description": "Get a work item from Azure DevOps",
  "parameters": {
    "type": "object",
    "properties": {
      "id": {"type": "number", "description": "Work item ID"},
      "project": {"type": "string", "description": "Project name"}
    },
    "required": ["id", "project"]
  }
}

VS Code

Install the MCP extension for VS Code and configure it:

1. Install MCP Extension:

   • Search for "Model Context Protocol" in VS Code extensions
   • Install the official MCP extension

2. Configure in VS Code settings.json:

   {
     "mcp.servers": {
       "azdevops": {
         "command": "npx",
         "args": ["-y","azdevops-mcp-alx"],
         "env": {
           "AZURE_DEVOPS_PAT": "your_personal_access_token",
           "AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/your-org"
         }
       }
     }
   }

3. Usage in VS Code:

   • Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P)
   • Type "MCP: Connect to Server"
   • Select "azdevops"
   • Use MCP tools in your AI-powered workflows

Other MCP-Compatible Tools

This server works with any MCP-compatible client. Common integration pattern:

# Start the server
node src/index.js

# Or use with MCP inspector for testing
npx @modelcontextprotocol/inspector node src/index.js

Development

• Dev mode: npm run dev
• Build: npm run build
• Test: npm test
• Inspect: npm run inspect

Azure DevOps Setup

1. Create Personal Access Token:

   • Go to Azure DevOps → User Settings → Personal Access Tokens
   • Create token with "Work Items (Read)" permissions
   • Copy the token to your .env file

2. Get Organization URL:

   • Format: https://dev.azure.com/your-organization-name
   • Or for on-premises: https://your-server/tfs/collection

Security Notes

• Never commit your .env file with real credentials
• Use environment variables in production
• Limit PAT permissions to minimum required scope
• Regularly rotate your Personal Access Tokens

License

ISC