1. Conduid
  2. Developer Tools
  3. Azure DevOps
MCP server · Developer Tools

Azure DevOps

A Model Context Protocol (MCP) server enabling AI assistants to interact with Azure DevOps services via Python SDK.

Unclaimed MIT last commit 11 months ago devtools
61Good

Scored 5 months ago · breakdown

About Azure DevOps

Azure DevOps is an MCP server published by Vortiago in the Developer Tools category: a Model Context Protocol (MCP) server enabling AI assistants to interact with Azure DevOps services via Python SDK.

The repository has 79 stars and 39 forks, with the last commit 11 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/Vortiago/mcp-azure-devops

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Azure DevOps

Powered by Claude · Grounded in docs

I know everything about Azure DevOps. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 5 days ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

MCP Azure DevOps Server

⚠️ NOTICE: Official Server Available

Please use the official Microsoft Azure DevOps MCP server instead:

https://github.com/microsoft/azure-devops-mcp

This repository is no longer maintained. The official Microsoft server provides better support, ongoing maintenance, and the latest features.


A Model Context Protocol (MCP) server enabling AI assistants to interact with Azure DevOps services.

Overview

This project implements a Model Context Protocol (MCP) server that allows AI assistants (like Claude) to interact with Azure DevOps, providing a bridge between natural language interactions and the Azure DevOps REST API.

Features

Currently implemented:

Work Item Management

  • Query Work Items: Search for work items using WIQL queries
  • Get Work Item Details: View complete work item information
  • Create Work Items: Add new tasks, bugs, user stories, and other work item types
  • Update Work Items: Modify existing work items' fields and properties
  • Add Comments: Post comments on work items
  • View Comments: Retrieve the comment history for a work item
  • Parent-Child Relationships: Establish hierarchy between work items

Project Management

  • Get Projects: View all accessible projects in the organization
  • Get Teams: List all teams within the organization
  • Team Members: View team membership information
  • Team Area Paths: Retrieve area paths assigned to teams
  • Team Iterations: Access team iteration/sprint configurations

Planned features:

  • Pipeline Operations: Query pipeline status and trigger new pipeline runs
  • Pull Request Handling: Create, update, and review Pull Requests
  • Sprint Management: Plan and manage sprints and iterations
  • Branch Policy Administration: Configure and manage branch policies

Getting Started

Prerequisites

  • Python 3.10+
  • Azure DevOps account with appropriate permissions
  • Personal Access Token (PAT) with necessary scopes for Azure DevOps API access

Installation

# Clone the repository
git clone https://github.com/Vortiago/mcp-azure-devops.git
cd mcp-azure-devops

# Install in development mode
uv pip install -e ".[dev]"

# Install from PyPi
pip install mcp-azure-devops

Configuration

Create a .env file in the project root with the following variables:

AZURE_DEVOPS_PAT=your_personal_access_token
AZURE_DEVOPS_ORGANIZATION_URL=https://your-organization.visualstudio.com or https://dev.azure.com/your-organisation

Note: Make sure to provide the full URL to your Azure DevOps organization.

Running the Server

# Development mode with the MCP Inspector
mcp dev src/mcp_azure_devops/server.py

# Install in Claude Desktop
mcp install src/mcp_azure_devops/server.py --name "Azure DevOps Assistant"

Usage Examples

Query Work Items

Show me all active bugs assigned to me in the current sprint

Create a Work Item

Create a user story in the ProjectX with the title "Implement user authentication" and assign it to john.doe@example.com

Update a Work Item

Change the status of bug #1234 to "Resolved" and add a comment explaining the fix

Team Management

Show me all the team members in the "Core Development" team in the "ProjectX" project

View Project Structure

List all projects in my organization and show me the iterations for the Development team

Development

The project is structured into feature modules, each implementing specific Azure DevOps capabilities:

  • features/work_items: Work item management functionality
  • features/projects: Project management capabilities
  • features/teams: Team management features
  • utils: Common utilities and client initialization

For more information on development, see the CLAUDE.md file.

Contributing

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

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

README fetched from the repository 5 days ago. The original is authoritative.

Questions

About Azure DevOps

How do I install Azure DevOps?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Azure DevOps safe to use with an AI agent?

Its trust score is 61 out of 100 (good). It passes 5 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Azure DevOps still maintained?

The last commit was 11 months ago and 15 open issues. That's long enough that you should check whether the maintainer is responding to issues before depending on it.