Azure DevOps MCP Server

What does “Azure DevOps” MCP Server do?

The Azure DevOps MCP (Model Context Protocol) Server enables AI assistants to interact seamlessly with Azure DevOps services by acting as a bridge between natural language requests and the Azure DevOps REST API. Through this server, AI-powered tools can perform a variety of DevOps-related tasks such as querying and managing work items, accessing project and team information, and automating DevOps workflows. By exposing Azure DevOps data and operations via the MCP interface, this server allows developers and teams to enhance productivity, streamline collaboration, and automate everyday DevOps operations directly from their AI assistants or integrated development environments.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

No explicit MCP resources are listed in the repository.

List of Tools

Based on the features described and the server’s capabilities, the following tools are provided by the Azure DevOps MCP Server:

• Query Work Items: Search for work items using WIQL queries.
• Get Work Item Details: Retrieve detailed information for specific work items.
• Create Work Items: Add new tasks, bugs, user stories, or other work item types.
• Update Work Items: Modify fields and properties of existing work items.
• Add Comments: Post comments to work items.
• View Comments: Retrieve comment history for a work item.
• Manage Parent-Child Relationships: Establish hierarchical relationships between work items.
• Get Projects: List all accessible projects.
• Get Teams: List all teams within an organization.
• Team Members: View team membership information.
• Team Area Paths: Retrieve area paths assigned to teams.
• Team Iterations: Access team iteration/sprint configurations.

Use Cases of this MCP Server

• Work Item Management: Developers can create, update, and monitor work items (e.g., tasks, bugs, user stories) via natural language, making backlog grooming and sprint planning more efficient.
• Project and Team Insights: Teams can quickly retrieve information about projects, teams, membership, and organizational structure, improving onboarding and cross-team collaboration.
• Automated Commenting and Auditing: AI assistants can add or retrieve comments on work items, assisting with documentation and communication within DevOps workflows.
• Sprint and Iteration Planning: Access to team iteration and area path data allows automated sprint planning, capacity allocation, and reporting.
• Hierarchy and Dependency Management: Establish and manage parent-child relationships between work items directly from conversational interfaces, streamlining complex project management tasks.

How to set it up

Windsurf

1. Prerequisites: Ensure Node.js is installed and you have a Personal Access Token (PAT) for Azure DevOps.
2. Install the Azure DevOps MCP Server: Install via pip or clone the repository and install.
3. Locate Configuration: Edit the Windsurf configuration file.
4. Add MCP Server: Add the MCP server using the following JSON snippet:

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

5. Save and Restart: Save your configuration and restart Windsurf to apply changes.

Securing API Keys (Windsurf)

Use environment variables in your configuration:

{
  "mcpServers": {
    "azure-devops": {
      "command": "python",
      "args": ["-m", "mcp_azure_devops.server"],
      "env": {
        "AZURE_DEVOPS_PAT": "${YOUR_PAT}",
        "AZURE_DEVOPS_ORGANIZATION_URL": "https://dev.azure.com/your-org"
      }
    }
  }
}

Claude

1. Prerequisites: Python 3.10+, Azure DevOps PAT.
2. Install Server: Install the package via pip or directly from source.
3. Find MCP Configuration: Open Claude’s configuration file.
4. Add MCP Server: Insert the following JSON:

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

5. Restart Claude: Restart the app to load the new MCP server.

Securing API Keys (Claude)

Use environment variables in your configuration:

{
  "mcpServers": {
    "azure-devops": {
      "command": "python",
      "args": ["-m", "mcp_azure_devops.server"],
      "env": {
        "AZURE_DEVOPS_PAT": "${YOUR_PAT}",
        "AZURE_DEVOPS_ORGANIZATION_URL": "https://dev.azure.com/your-org"
      }
    }
  }
}

Cursor

1. Prerequisites: Install Python and obtain your Azure DevOps PAT.
2. Install Package: Use pip to install the MCP server.
3. Open Cursor Settings: Edit the settings file.
4. Insert MCP Server:

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

5. Restart Cursor: Restart the app.

Securing API Keys (Cursor)

{
  "mcpServers": {
    "azure-devops": {
      "command": "python",
      "args": ["-m", "mcp_azure_devops.server"],
      "env": {
        "AZURE_DEVOPS_PAT": "${YOUR_PAT}",
        "AZURE_DEVOPS_ORGANIZATION_URL": "https://dev.azure.com/your-org"
      }
    }
  }
}

Cline

1. Ensure prerequisites: Python 3.10+, Azure DevOps PAT.
2. Install MCP Server: Use pip or download and install from source.
3. Edit Cline Configuration: Locate and edit the configuration file.
4. Add MCP Server:

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

5. Restart Cline: Save and restart to activate the server.

Securing API Keys (Cline)

{
  "mcpServers": {
    "azure-devops": {
      "command": "python",
      "args": ["-m", "mcp_azure_devops.server"],
      "env": {
        "AZURE_DEVOPS_PAT": "${YOUR_PAT}",
        "AZURE_DEVOPS_ORGANIZATION_URL": "https://dev.azure.com/your-org"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "azure-devops": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “azure-devops” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available documentation, this MCP server provides solid core functionality for Azure DevOps integration, with clear setup instructions and tool coverage, but lacks explicit prompt templates and resource descriptions. It does not document Roots or sampling support. Therefore, I would rate this MCP server a solid 7/10 for practical usability and documentation completeness.

MCP Score