Azure DevOps MCP Server

Azure DevOps MCP Server

Provides Azure DevOps tooling for AI agents, enabling interaction with projects, work items, repositories, and pipelines through natural language.

Category
访问服务器

README

⭐ Azure DevOps MCP Server

[!IMPORTANT] The Azure DevOps Remote MCP Server is now available in public preview for all organizations. We recommend migrating to the Remote MCP Server going forward.

Learn more

This project provides Azure DevOps MCP tooling for AI agents, with a remote-first onboarding experience and a local server option when you need it.

📄 Table of Contents

  1. 📺 Overview
  2. 🏆 Expectations
  3. 🚀 Remote MCP Server (Recommended)
  4. ⚙️ Supported Tools
  5. 🔌 Local MCP Server Installation (Optional)
  6. 🌏 Using Domains (local)
  7. 🐥 Project and Team Defaults (local)
  8. 📝 Troubleshooting
  9. 🎩 Examples & Best Practices
  10. 🙋‍♀️ Frequently Asked Questions
  11. 📌 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"

🏆 Expectations

The Azure DevOps MCP Server is built around tools that are concise, simple, focused, and easy to use, with each one designed for a specific scenario. We intentionally avoid creating complex tools that try to do too much. The goal is to provide a thin abstraction layer over the REST APIs that makes data access straightforward while allowing the language model to handle the more complex reasoning.

🚀 Remote MCP Server (Recommended)

The Azure DevOps Remote MCP Server is now available in public preview.

Over time, the Remote MCP Server will replace this local MCP Server. We will continue to support the local server for now, but future investments will primarily focus on the remote experience.

We encourage all users of the local MCP Server to begin migrating to the Remote MCP Server.

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.

[!WARNING] Internal Microsoft users of the Remote MCP Server should not create issues in this repository. Please use the dedicated Teams channel instead.

For complete instructions, see the Remote MCP Server onboarding documentation.

Quick start with .vscode/mcp.json

Use this configuration to connect directly to the Azure DevOps-hosted endpoint using streamable HTTP transport:

{
  "servers": {
    "ado-remote-mcp": {
      "url": "https://mcp.dev.azure.com/{organization}",
      "type": "http"
    }
  },
  "inputs": []
}

See documentation for additional configuration 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 a comprehensive 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 stdio setup.

Use this section if you specifically need the local stdio server experience. For most users, start with the Remote MCP Server section above.

For the best experience, use Visual Studio Code and GitHub Copilot. See the getting started documentation to use our MCP Server with other tools such as Visual Studio 2022, Codex, Claude Code, Cursor, Opencode, and Kilocode.

Prerequisites

  1. Install VS Code or VS Code Insiders
  2. Install Node.js 20+
  3. Open VS Code in an empty folder

Installation

🧨 Install from Public Feed

This installation method is the easiest for all users of Visual Studio Code.

🎥 Watch this quick start video to get up and running in under two minutes!

Steps

In your project, add a .vscode\mcp.json file with the following content:

{
  "inputs": [
    {
      "id": "ado_org",
      "type": "promptString",
      "description": "Azure DevOps organization name  (e.g. 'contoso')"
    }
  ],
  "servers": {
    "ado": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@azure-devops/mcp", "${input:ado_org}"]
    }
  }
}

🔥 To stay up to date with the latest features, you can use our nightly builds. Simply update your mcp.json configuration to use @azure-devops/mcp@next. Here is an updated example:

{
  "inputs": [
    {
      "id": "ado_org",
      "type": "promptString",
      "description": "Azure DevOps organization name  (e.g. 'contoso')"
    }
  ],
  "servers": {
    "ado": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@azure-devops/mcp@next", "${input:ado_org}"]
    }
  }
}

Save the file, then click 'Start'.

start mcp server

In chat, switch to Agent Mode.

Click "Select Tools" and choose the available tools.

configure mcp server tools

Open GitHub Copilot Chat and try a prompt like List ADO projects. The first time an ADO tool is executed browser will open prompting to login with your Microsoft account. Please ensure you are using credentials matching selected Azure DevOps organization.

💥 We strongly recommend creating a .github\copilot-instructions.md in your project. This will enhance your experience using the Azure DevOps MCP Server with GitHub Copilot Chat. To start, just include "This project uses Azure DevOps. Always check to see if the Azure DevOps MCP server has a tool relevant to the user's request" in your copilot instructions file.

See the getting started documentation to use our MCP Server with other tools such as Visual Studio 2022, Codex, Claude Code, and Cursor.

🌏 Using Domains (local)

Azure DevOps exposes a large surface area. As a result, our Azure DevOps MCP Server includes many tools. To keep the toolset manageable, avoid confusing the model, and respect client limits on loaded tools, use Domains to load only the areas you need. Domains are named groups of related tools (for example: core, work, work-items, repositories, wiki). Add the -d argument and the domain names to the server args in your mcp.json to list the domains to enable.

For example, use "-d", "core", "work", "work-items" to load only Work Item related tools (see the example below).

{
  "inputs": [
    {
      "id": "ado_org",
      "type": "promptString",
      "description": "Azure DevOps organization name  (e.g. 'contoso')"
    }
  ],
  "servers": {
    "ado_with_filtered_domains": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@azure-devops/mcp", "${input:ado_org}", "-d", "core", "work", "work-items"]
    }
  }
}

Domains that are available are: core, work, work-items, search, test-plans, repositories, wiki, pipelines, advanced-security

We recommend that you always enable core tools so that you can fetch project level information.

By default all domains are loaded

🐥 Project and Team Defaults (local)

You can also configure default Azure DevOps project and team values from .vscode/mcp.json using project and team, so tools can skip selection prompts.

Example .vscode/mcp.json

{
  "servers": {
    "ado": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@azure-devops/mcp", "myorg", "--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 & Best Practices

Explore example prompts in our Examples documentation.

For best practices and tips to enhance your experience with the MCP Server, refer to the How-To guide.

🙋‍♀️ 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, please file issues for bugs, enhancements, or documentation improvements.

See our Contributions Guide for:

  • 🛠️ Development setup
  • ✨ Adding new tools
  • 📝 Code style & testing
  • 🔄 Pull request process

⚠️ Please 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.

📈 Project Stats

Star History Chart

🏆 Hall of Fame

Thanks to all contributors who make this project awesome! ❤️

Contributors

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.

<!-- version: 2023-04-07 [Do not delete this line, it is used for analytics that drive template improvements] -->

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选