What is the Azure DevOps MCP Server?

The Azure DevOps MCP Server is a component that integrates Azure DevOps with AI agents, allowing these agents to interact with Azure DevOps services like work items, repositories, and pipelines.

What is MCP (Model Context Protocol)?

MCP stands for Model Context Protocol. It’s an open protocol that standardizes how applications provide context to LLMs, enabling AI models to access and interact with external data sources and tools.

What are the prerequisites for installing the Azure DevOps MCP Server?

Prerequisites include Node.js (v20 LTS or higher), npm, an MCP-compatible client (e.g., Cline or Claude Desktop), and an Azure DevOps account with access tokens.

How do I install the Azure DevOps MCP Server?

You can install it via Smithery using the command npx -y @smithery/cli install @RainyCodeWizard/azure-devops-mcp-server --client claude or manually by cloning the repository, installing dependencies, and building the server.

How do I configure the Azure DevOps MCP Server?

Configuration involves obtaining an Azure DevOps Personal Access Token (PAT) and adding the server configuration to your Cline MCP settings file, specifying the server command, environment variables (AZURE_DEVOPS_ORG, AZURE_DEVOPS_PAT, AZURE_DEVOPS_PROJECT_ID), and other settings.

What scopes are required for the Azure DevOps Personal Access Token (PAT)?

The PAT requires the following scopes:

• Code (read, write) - For Pull Request operations
• Work Items (read, write) - For Work Item management
• Build (read, execute) - For Pipeline operations
• Wiki (read, write) - For Wiki operations
• Project and Team (read) - For Project and Board information

What tools are available in the Azure DevOps MCP Server?

Available tools include:

• Work Items: get_work_item, list_work_items, create_work_item, update_work_item
• Boards: get_boards
• Git: list_repositories, get_file, compare_branches
• Pipelines: list_pipelines, trigger_pipeline
• Pull Requests: list_pull_requests, create_pull_request, update_pull_request, get_pull_request
• Wiki: get_wikis, get_wiki_page, create_wiki, update_wiki_page
• Projects: list_projects

How do I verify that the Azure DevOps MCP Server is working correctly?

You can verify the installation using the MCP Inspector by running the command npm run inspector.

What do I do if the server isn’t connecting?

Check that the path in your MCP settings is correct, verify your Azure DevOps credentials, and check the Cline logs for any error messages.

What do I do if I get authentication errors?

Verify your PAT hasn’t expired, ensure the PAT has all necessary scopes, and double-check the organization and project ID.

Can I modify or extend the server?

Yes, you can modify the server by making changes in the src directory, running npm run watch for development, and building with npm run build when ready. Test using the inspector: npm run inspector.

What is UBOS?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model, and create Multi-Agent Systems.