Azure DevOps MCP
Integrates Cline with Azure DevOps services, enabling access to work items, repositories, and pull requests through configurable MCP tools.
What is Azure DevOps MCP?
Azure DevOps MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to integrates cline with azure devops services, enabling access to work items, repositories, and pull requests through configurable mcp tools.
Integrates Cline with Azure DevOps services, enabling access to work items, repositories, and pull requests through configurable MCP tools.
This server falls under the Version Control and Developer Tools categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Integrates Cline with Azure DevOps services, enabling access
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx azure-devops-mcp-server-for-clineConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Azure DevOps MCP
The Azure DevOps MCP Server bridges your AI assistant (Cline or Claude Desktop) with Azure DevOps, giving it direct access to work items, pull requests, pipelines, boards, wikis, and project listings. Rather than copy-pasting DevOps data into chat, you can ask natural language questions and let the server retrieve or mutate resources in real time. It is especially useful for development teams that manage sprints, code reviews, and CI/CD pipelines inside Azure DevOps and want AI-assisted triage, PR creation, or backlog grooming without leaving their editor.
Prerequisites
- Node.js v20 LTS or higher and npm installed
- An Azure DevOps account with a Personal Access Token (PAT) scoped to Code, Work Items, Build, Wiki, and Project/Team read permissions
- The repository cloned locally so you can build the TypeScript source (no published npm package)
- Cline (VSCode extension) or Claude Desktop as your MCP client
Clone and build the server
Clone the repository, install dependencies, and compile the TypeScript source. The build output lands in the build/ directory which is not committed to version control.
git clone https://github.com/stefanskiasan/azure-devops-mcp-server.git
cd azure-devops-mcp-server
npm install
npm run buildGenerate an Azure DevOps Personal Access Token
In Azure DevOps, go to User Settings > Security > Personal Access Tokens and create a new token. Grant the following scopes: Code (read, write), Work Items (read, write), Build (read, execute), Wiki (read, write), and Project and Team (read). Copy the token immediately as it will not be shown again.
Add the server to your MCP client configuration
Open your MCP settings file. For Cline it lives at %APPDATA%/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json; for Claude Desktop at %LOCALAPPDATA%/Claude/claude_desktop_config.json on Windows or ~/Library/Application Support/Claude/claude_desktop_config.json on macOS. Add the mcpServers entry below, replacing the placeholder values with your real paths and credentials.
Verify the server is connected
Restart Cline or Claude Desktop after saving the config. You can also run the built-in inspector to confirm tools are registered without needing a client.
npm run inspectorStart querying Azure DevOps through your AI assistant
With the server running, your AI assistant can now list projects, create work items, manage pull requests, trigger pipelines, and read or update wiki pages using natural language.
Azure DevOps MCP Examples
Client configuration
Add this block to your cline_mcp_settings.json or claude_desktop_config.json, replacing the path and credential placeholders with real values.
{
"mcpServers": {
"azure-devops": {
"command": "node",
"args": ["/absolute/path/to/azure-devops-mcp-server/build/index.js"],
"env": {
"AZURE_DEVOPS_ORG": "your-organization",
"AZURE_DEVOPS_PAT": "your-personal-access-token",
"AZURE_DEVOPS_PROJECT": "your-project-name"
},
"disabled": false,
"autoApprove": []
}
}
}Prompts to try
Once configured, use these prompts with Cline or Claude Desktop to exercise the server's tools.
- "List all active work items assigned to me in the current sprint"
- "Create a Bug work item titled 'Login page throws 500 on empty password' with high priority"
- "Show me all open pull requests in the main repository"
- "Trigger the nightly-build pipeline"
- "Get the content of the Architecture wiki page"Troubleshooting Azure DevOps MCP
The server is not listed in Cline's capabilities after restarting
Double-check the absolute path in your config — the build/ directory must exist. Run 'npm run build' in the cloned repository if you haven't already, then confirm the path points to build/index.js.
Authentication errors when calling tools
Verify the PAT has not expired and includes all required scopes (Code, Work Items, Build, Wiki, Project and Team). Also confirm AZURE_DEVOPS_ORG matches the exact organization slug in your Azure DevOps URL.
Work item queries return no results
Ensure AZURE_DEVOPS_PROJECT is set to the correct project name (case-sensitive). Use the list_projects tool first to confirm the available project names.
Frequently Asked Questions about Azure DevOps MCP
What is Azure DevOps MCP?
Azure DevOps MCP is a Model Context Protocol (MCP) server that integrates cline with azure devops services, enabling access to work items, repositories, and pull requests through configurable mcp tools. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Azure DevOps MCP?
Follow the installation instructions on the Azure DevOps MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Azure DevOps MCP?
Azure DevOps MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Azure DevOps MCP free to use?
Yes, Azure DevOps MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Azure DevOps MCP Alternatives — Similar Version Control Servers
Looking for alternatives to Azure DevOps MCP? Here are other popular version control servers you can use with Claude, Cursor, and VS Code.
Ruiyu MA
★ 30.1kConnect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
GitMCP
★ 8.1kTransforms any GitHub repository or GitHub Pages site into a documentation hub for AI assistants using the Model Context Protocol. It allows AI tools to access real-time code and documentation to prevent hallucinations and provide accurate API usage
GitHub Codemunch
★ 1.8kA token-efficient MCP server for exploring GitHub repositories using tree-sitter AST parsing to extract symbol signatures and summaries. It enables users to search and retrieve specific code components while significantly reducing token consumption c
Azure DevOps MCP Server
★ 1.7kThis server provides a convenient API for interacting with Azure DevOps services, enabling AI assistants and other tools to manage work items, code repositories, boards, sprints, and more. Built with the Model Context Protocol, it provides a standard
GitHub Official
★ 1.2kOfficial GitHub integration with comprehensive API coverage
Azure DevOps
★ 367Enables interaction with Azure DevOps through Cursor chat, providing tools to manage builds, pipelines, work items, sprints, and board operations. Supports secure authentication via Personal Access Tokens and allows natural language-driven DevOps tas
Browse More Version Control MCP Servers
Explore all version control servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Azure DevOps MCP 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 MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.