MCP Server for Azure DevOps

MCP Server for Azure DevOps

Provides AI assistants with comprehensive access to Azure DevOps services including work items, repositories, pull requests, wikis, builds, pipelines, and test plans through 25+ MCP tools with multi-project support.

Category
访问服务器

README

MCP Server for Azure DevOps

A comprehensive Model Context Protocol (MCP) server that provides AI assistants with full access to Azure DevOps services.

License: MIT Node.js

🚀 Quick Install

# Clone the repository
git clone https://github.com/sepal7/mcp-ado.git
cd mcp-ado

# Install dependencies
npm install

# Create .env file
cp .env.example .env
# Edit .env with your Azure DevOps credentials

# Test the connection
npm run test-connection

Then configure your IDE (see Installation section below).

📦 Available Tools (25+)

Wiki (3 tools)

  • get_wiki_page - Retrieve wiki page by ID or path
  • list_wiki_pages - List all wiki pages in a project
  • search_wiki_pages - Search wiki pages by content or title

Repositories (5 tools)

  • list_repos - List all repositories
  • get_repo - Get repository details
  • get_repo_file - Get file content from repository
  • list_repo_branches - List branches in a repository
  • search_code - Search code across repositories

Work Items (5 tools)

  • get_work_item - Get work item by ID
  • get_work_items - Get multiple work items
  • query_work_items - Query work items using WIQL
  • create_work_item - Create new work item
  • update_work_item - Update existing work item

Pull Requests (3 tools)

  • list_pull_requests - List pull requests
  • get_pull_request - Get pull request details
  • get_pr_comments - Get PR review comments

Builds & Pipelines (4 tools)

  • list_builds - List recent builds
  • get_build - Get build details
  • list_pipelines - List pipelines
  • get_pipeline_run - Get pipeline run details

Releases (2 tools)

  • list_releases - List releases
  • get_release - Get release details

Test Plans (2 tools)

  • list_test_plans - List test plans
  • get_test_plan - Get test plan details

Generic (1 tool)

  • ado_api_call - Make any Azure DevOps REST API call

🌟 Comparison with Similar Projects

Feature This Project Other MCP ADO Servers
Total Tools 25+ 5-15
Wiki Support ✅ Yes (3 tools) ❌ Limited/None
Multi-Project ✅ Built-in ❌ Single project
WIQL Queries ✅ Yes ❌ No
Generic API Tool ✅ Yes ❌ No
Helper Scripts ✅ PAT management ❌ No
Documentation ✅ Comprehensive ⚠️ Basic

Key Differentiators:

  • Most comprehensive tool coverage (25+ vs 5-15)
  • Multi-project support without reconfiguration
  • Advanced features (WIQL queries, generic API tool)
  • Better developer experience (helper scripts, comprehensive docs)

✨ Features

  • 25+ MCP Tools covering all major Azure DevOps services
  • Multi-Project Support - Access any project in your organization without reconfiguration
  • WIQL Query Support - Advanced work item querying using Work Item Query Language
  • Generic API Tool - Make any Azure DevOps REST API call for future-proof extensibility
  • Helper Scripts - Automated PAT token management and connection testing
  • Comprehensive Documentation - Step-by-step guides for Cursor, VS Code, and deployment

🚀 Quick Start

Prerequisites

  • Node.js 18+ installed
  • Azure DevOps Personal Access Token (PAT) with appropriate permissions
  • VS Code with GitHub Copilot Chat extension, VS Code Insiders, or Cursor IDE

Installation

📦 Install from Source

# Clone the repository
git clone https://github.com/sepal7/mcp-ado.git
cd mcp-ado

# Install dependencies
npm install

# Create .env file
cp .env.example .env
# Edit .env with your values:
# AZURE_DEVOPS_ORG=YourOrganization
# AZURE_DEVOPS_PROJECT=YourProject
# AZURE_DEVOPS_PAT=your_pat_token_here

# Test the connection
npm run test-connection

Then configure manually (see detailed guides below).

For detailed setup instructions, see:

🎯 Usage Examples

Once configured, use natural language to interact with Azure DevOps:

Default Project:

  • "List all repositories"
  • "Get work item #12345"
  • "Show me pull requests"

Other Projects:

  • "List repositories in the [ProjectName] project"
  • "Get work items from the [ProjectName] project"

All tools support an optional project parameter to access any project in your organization.

⚙️ Configuration

Environment Variables

Variable Required Description
AZURE_DEVOPS_ORG Yes Your Azure DevOps organization name
AZURE_DEVOPS_PROJECT Yes Default project name
AZURE_DEVOPS_PAT Yes Personal Access Token
APPLICATIONINSIGHTS_CONNECTION_STRING No Optional telemetry connection string

Multi-Project Support

All MCP tools support an optional project parameter. When using Cursor or VS Code, mention the project name in your request:

"List repositories in the [ProjectName] project"

The AI assistant automatically extracts the project name and passes it to the MCP tool.

📁 Project Structure

mcp-ado/
├── server.js              # Main MCP server implementation
├── package.json           # Node.js dependencies and scripts
├── .env.example           # Environment variables template
├── README.md              # This file
│
├── docs/                  # Documentation
│   ├── 01-SETUP.md        # General setup guide
│   ├── 02-CURSOR-SETUP.md # Cursor IDE setup
│   ├── 03-VSCODE-SETUP.md # VS Code setup
│   ├── 04-PAT-MANAGEMENT.md # PAT token management
│   ├── 05-RESTART-SERVER.md # How to restart server
│   ├── 07-CHANGELOG.md     # Version history
│   └── 08-ONPREMISE-WINDOWS-IIS.md # On-premise deployment
│
├── scripts/               # Utility scripts
│   ├── test.js            # Basic server tests
│   ├── test-connection.js # Azure DevOps connection tester
│   └── update-pat.ps1     # PAT token updater script
│
└── azure/                 # Azure deployment files
    ├── README.md          # Azure deployment guide
    ├── Dockerfile         # Container image definition
    └── azure-deploy.bicep # Infrastructure as code

📚 Documentation

🤝 Contributing

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

📄 License

MIT License - see LICENSE file for details

🙏 Credits


Made with ❤️ for the MCP community

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