Azure DevOps
A Model Context Protocol server that enables AI assistants to interact with Azure DevOps services, allowing users to query work items with plans to support creating/updating items, managing pipelines, handling pull requests, and administering sprints
What is Azure DevOps?
Azure DevOps is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that enables ai assistants to interact with azure devops services, allowing users to query work items with plans to support creating/updating items, managing pipelines, h...
A Model Context Protocol server that enables AI assistants to interact with Azure DevOps services, allowing users to query work items with plans to support creating/updating items, managing pipelines, handling pull requests, and administering sprints
This server falls under the Developer Tools and Business Applications categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol server that enables AI assistants t
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-azure-devops-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Azure DevOps
The MCP Azure DevOps server connects AI assistants to Azure DevOps via a Python-based MCP server that authenticates with a Personal Access Token. It exposes tools for querying and creating work items using WIQL, managing comments and parent-child relationships, listing projects and teams, and accessing sprint and iteration data — allowing developers to interact with their Azure DevOps organization through natural language without leaving their AI client.
Prerequisites
- Python 3.10 or higher with pip or uv package manager
- An Azure DevOps account with access to at least one organization
- An Azure DevOps Personal Access Token (PAT) with Work Items (Read & Write) and Project (Read) scopes
- Your organization URL in the format https://dev.azure.com/your-organisation or https://your-org.visualstudio.com
- An MCP-compatible client such as Claude Desktop
Install the mcp-azure-devops Python package
Install the server package using pip. Using a virtual environment is recommended to avoid dependency conflicts.
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install mcp-azure-devopsCreate an Azure DevOps Personal Access Token
In Azure DevOps, go to User Settings > Personal Access Tokens > New Token. Grant it Read & Write access for Work Items and Read for Code and Project. Copy the token — it is only shown once.
Set environment variables
Export the required environment variables. AZURE_DEVOPS_ORGANIZATION_URL is your org root URL and AZURE_DEVOPS_PAT is the token you just created.
export AZURE_DEVOPS_ORGANIZATION_URL="https://dev.azure.com/your-organisation"
export AZURE_DEVOPS_PAT="your-personal-access-token"Add the server to your MCP client configuration
Open claude_desktop_config.json and add the Azure DevOps server entry. Pass the environment variables directly in the env block so the MCP client sets them when spawning the server process.
{
"mcpServers": {
"azure-devops": {
"command": "/path/to/.venv/bin/python",
"args": ["-m", "mcp_azure_devops.server"],
"env": {
"AZURE_DEVOPS_ORGANIZATION_URL": "https://dev.azure.com/your-organisation",
"AZURE_DEVOPS_PAT": "your-personal-access-token"
}
}
}
}Restart your MCP client and verify
Restart Claude Desktop. Ask the assistant to list your Azure DevOps projects to confirm the connection is working.
Azure DevOps Examples
Client configuration
Complete claude_desktop_config.json entry for the mcp-azure-devops server using a Python virtual environment.
{
"mcpServers": {
"azure-devops": {
"command": "/Users/yourname/.venv/bin/python",
"args": ["-m", "mcp_azure_devops.server"],
"env": {
"AZURE_DEVOPS_ORGANIZATION_URL": "https://dev.azure.com/your-organisation",
"AZURE_DEVOPS_PAT": "your_pat_here"
}
}
}
}Prompts to try
Example prompts that use the work item query, creation, and project management tools exposed by the server.
- "List all projects in my Azure DevOps organization"
- "Show me all active bugs assigned to me in the current sprint"
- "Create a user story titled 'Add dark mode toggle' in the FrontendApp project"
- "What work items are in the current sprint for team Alpha?"
- "Add a comment to work item #1234 saying the fix is deployed to staging"Troubleshooting Azure DevOps
Authentication error: 401 Unauthorized
Verify your AZURE_DEVOPS_PAT is correct and has not expired. PATs have a maximum lifetime of one year. Also confirm AZURE_DEVOPS_ORGANIZATION_URL is the root org URL (e.g. https://dev.azure.com/myorg), not a project URL.
Work item queries return empty results
Ensure your PAT has 'Work Items (Read)' scope. WIQL queries are case-sensitive for field names. Try a simple query first: 'List all projects' to confirm connectivity before running complex WIQL.
Module not found error when starting the server
Ensure you are using the virtual environment where mcp-azure-devops is installed. The command in your MCP config must point to the Python binary inside the venv (e.g. /path/to/.venv/bin/python), not the system Python.
Frequently Asked Questions about Azure DevOps
What is Azure DevOps?
Azure DevOps is a Model Context Protocol (MCP) server that model context protocol server that enables ai assistants to interact with azure devops services, allowing users to query work items with plans to support creating/updating items, managing pipelines, handling pull requests, and administering sprints It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Azure DevOps?
Follow the installation instructions on the Azure DevOps GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Azure DevOps?
Azure DevOps works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Azure DevOps free to use?
Yes, Azure DevOps is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Azure DevOps Alternatives — Similar Developer Tools Servers
Looking for alternatives to Azure DevOps? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Azure DevOps in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Azure DevOps?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.