Allows AI agents to interact with Azure DevOps to manage projects, work items, repositories, wikis, and pipelines.
Also known as microsoft/azure-devops-mcp, azure-devops-mcp
- Stars
- 2,086
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- v0.0.1
- Last commit
- Nov 13, 2026
- License
- MIT
What is Azure DevOps MCP?
Azure DevOps allows AI agents to interact with Azure DevOps to manage projects, work items, repositories, wikis, and pipelines.
Summary generated from the project's README
About Azure DevOps MCP server
Managing software development lifecycles through AI agents is possible with the Azure DevOps MCP Server. This tool allows developers to connect their AI clients to Azure DevOps to handle tasks involving projects, work items, repositories, wikis, and pipelines. It acts as a thin layer over REST APIs, enabling agents to perform high-level reasoning based on your organization's data.
You can choose between a remote server setup, which is the recommended method for simplicity, or a local server using a stdio connection. The local version supports domain filtering through specific groups like work-items, repositories, and pipelines to help manage tool limits in your client. Users can configure default projects and teams in their settings to streamline interactions.
To use the local server, you need Node.js 20 or later and a Microsoft account with access to your organization. It is compatible with various clients including VS Code, GitHub Copilot, Claude Code, and Cursor. The remote version is prioritized for new features and requires an organization name for configuration.
What you can do with it
- 1Manage project documentationAn AI agent can create or update wiki pages to keep system design or onboarding instructions current.
- 2Track development progressDevelopers can ask an agent to list work items within a specific project iteration or team.
- 3Audit repository and build statusYou can use an agent to quickly retrieve lists of repositories or builds for a specific project.
- 4Organize testing workflowsAn agent can retrieve information regarding existing test plans within your Azure DevOps environment.
Written from the project's README. Every use case is checked against a quote from it.
How to install Azure DevOps MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Azure DevOps MCP in Claude Code
$ claude mcp add --transport http azure-devops-mcp https://mcp.dev.azure.com/Install Azure DevOps MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"azure-devops-mcp": {
"url": "https://mcp.dev.azure.com/"
}
}
}Install Azure DevOps MCP in VS Code
.vscode/mcp.json
{
"servers": {
"azure-devops-mcp": {
"type": "http",
"url": "https://mcp.dev.azure.com/"
}
}
}Install Azure DevOps MCP in VS Code CLI
$ code --add-mcp '{"name":"azure-devops-mcp","type":"http","url":"https://mcp.dev.azure.com/"}'Install Azure DevOps MCP in Codex
$ codex mcp add azure-devops-mcp --url https://mcp.dev.azure.com/Install Azure DevOps MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.azure-devops-mcp] url = "https://mcp.dev.azure.com/"
Install Azure DevOps MCP in Gemini CLI
$ gemini mcp add -s user --transport http azure-devops-mcp https://mcp.dev.azure.com/Install Azure DevOps MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"azure-devops-mcp": {
"url": "https://mcp.dev.azure.com/",
"type": "http"
}
}
}Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubAzure DevOps MCP Server
[!IMPORTANT] We recommend using the Remote MCP Server instead of this local server. It requires no installation and gets new features first.
This project gives AI agents access to Azure DevOps through the Model Context Protocol (MCP). Use the hosted remote server for the simplest setup, or run the local server when you need a stdio connection.
Table of Contents
- Overview
- Design
- Remote MCP Server (Recommended)
- Supported Tools
- Local MCP Server Installation (Optional)
- Using Domains (Local Server)
- Project and Team Defaults (Local Server)
- Troubleshooting
- Examples and Best Practices
- Frequently Asked Questions
- Contributing
Overview
The Azure DevOps MCP Server brings Azure DevOps context to your agents. Try prompts like:
- "List my ADO projects"
- "List ADO Builds for 'Contoso'"
- "List ADO Repos for 'Contoso'"
- "List test plans for 'Contoso'"
- "List teams for project 'Contoso'"
- "List iterations for project 'Contoso'"
- "List my work items for project 'Contoso'"
- "List work items in current iteration for 'Contoso' project and 'Contoso Team'"
- "List all wikis in the 'Contoso' project"
- "Create a wiki page '/Architecture/Overview' with content about system design"
- "Update the wiki page '/Getting Started' with new onboarding instructions"
- "Get the content of the wiki page '/API/Authentication' from the Documentation wiki"
Design
Each tool handles a focused Azure DevOps task. The server provides a thin layer over the REST APIs, while the AI agent handles higher-level reasoning.
Remote MCP Server (Recommended)
For complete instructions, see the Remote MCP Server onboarding documentation.
The remote server will eventually replace the local server. The local server remains supported, but new development will focus on the remote server. Existing local server users should begin planning their migration.
If you encounter issues with tools, need support, or have a feature request, you can report an issue using the Remote MCP Server issue template. During the preview period, we will track Remote MCP Server issues through this repository.
Quick Start
Create .vscode/mcp.json in your project and add this configuration. Replace {organization} with your Azure DevOps organization name.
{
"servers": {
"ado-remote-mcp": {
"url": "https://mcp.dev.azure.com/{organization}",
"type": "http"
}
},
"inputs": []
}
See the remote server configuration documentation for more options.
After saving .vscode/mcp.json, start the server from the MCP view in VS Code, then run a prompt like List ADO projects.
Supported Tools
See the Available Tools documentation for the complete list of available remote tools.
For the complete list of local tools, see TOOLSET.md.
Local MCP Server Installation (Optional)
[!IMPORTANT] Start with the Remote MCP Server first. Use the local MCP Server only if your scenario specifically requires a local
stdiosetup.
These steps use Visual Studio Code and GitHub Copilot. For other supported clients, including Visual Studio 2022, Codex, Claude Code, Cursor, OpenCode, and Kilo Code, see the getting started guide.
Prerequisites
- Install VS Code or VS Code Insiders.
- Install Node.js 20 or later.
- Open your project in VS Code.
Installation
Install from npm
- Create
.vscode/mcp.jsonin your project. - Add this configuration:
{
"servers": {
"ado": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@azure-devops/mcp", "{organization}"]
}
}
}
- Save the file, then start the
adoserver from the MCP view in VS Code. - Open GitHub Copilot Chat and switch to Agent mode.
- Select the Azure DevOps tools, then try a prompt such as
List ADO projects. - When prompted, sign in with a Microsoft account that has access to the selected Azure DevOps organization.
To use nightly builds, replace @azure-devops/mcp with @azure-devops/mcp@next in the configuration.
For better tool selection, add .github/copilot-instructions.md to your project with this instruction:
This project uses Azure DevOps. Always check whether the Azure DevOps MCP server has a tool relevant to the user's request.
Using Domains (Local Server)
The local server includes many tools. Domains let you load only the tool groups you need, which keeps the tool list manageable and helps clients with tool limits. Available domains are core, work, work-items, search, test-plans, repositories, wiki, pipelines, and advanced-security.
Add -d followed by the domains to the server arguments. For example, this configuration loads only work item-related tools:
{
"servers": {
"ado_with_filtered_domains": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@azure-devops/mcp", "{organization}", "-d", "core", "work", "work-items"]
}
}
}
Always include core so the agent can retrieve project information.
If you omit
-d, the server loads all domains.
Project and Team Defaults (Local Server)
Set default Azure DevOps project and team values in .vscode/mcp.json so tools can skip selection prompts.
Example .vscode/mcp.json
{
"servers": {
"ado": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@azure-devops/mcp", "{organization}", "--authentication", "azcli"],
"env": {
"ado_mcp_project": "Contoso",
"ado_mcp_team": "Fabrikam Team"
}
}
}
}
Troubleshooting
See the Troubleshooting guide for help with common issues and logging.
Examples
See the examples for sample prompts.
Frequently Asked Questions
For answers to common questions about the Azure DevOps MCP Server, see the Frequently Asked Questions.
Contributing
We welcome contributions. During preview, file issues for bugs, enhancements, or documentation improvements.
See our Contributions Guide for:
- Development setup
- Adding new tools
- Code style and testing
- Pull request process
Read the Contributions Guide before creating a pull request.
Code of Conduct
This project follows the Microsoft Open Source Code of Conduct. For questions, see the FAQ or contact open@microsoft.com.
Hall of Fame
Thanks to all contributors who make this project awesome! ❤️
Generated with contrib.rocks
License
Licensed under the MIT License.
Trademarks: This project may include trademarks or logos for Microsoft or third parties. Use of Microsoft trademarks or logos must follow Microsoft’s Trademark & Brand Guidelines. Third-party trademarks are subject to their respective policies.
Azure DevOps MCP questions
How do I add Azure DevOps MCP to Claude Code?
Run claude mcp add --transport http azure-devops-mcp https://mcp.dev.azure.com/ in your terminal. Add --scope user to make it available in every project.
How do I add Azure DevOps MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How can I limit the number of tools loaded by the local server?
You can use domains to load only specific tool groups like core, work, or repositories to keep the tool list manageable.
Can I set default projects and teams for the local server?
Yes, you can set default Azure DevOps project and team values in your configuration file so tools can skip selection prompts.