Azure MCP FastMCP Server
Provides Azure DevOps integration through MCP, enabling management of projects, work items, teams, and policies via natural language. Supports bulk work item creation with hierarchical relationships and iteration assignments.
README
Azure MCP FastMCP Server
A Model Context Protocol (MCP) server that provides Azure DevOps integration through a set of tools for managing projects, work items, teams.
Table of Contents
- Azure MCP FastMCP Server
🚀 Features
- Standalone Executable: No dependencies required when using npx
- Azure DevOps Integration: Full access to Azure DevOps REST API
- MCP Protocol: Compatible with any MCP client
- Multiple Tools: Projects, Work Items, Teams, and Policies management
📦 Installation
Using npx (Recommended)
# No installation required - runs directly
npx -y @ahmedrowaihi/azure-mcp-fastmcp
Local Development
# Clone the repository
git clone https://github.com/ahmedrowaihi/azure-mcp-fastmcp.git
cd azure-mcp-fastmcp
# Install dependencies
bun install
# Build the project
bun run build
# Run the built server
bun run dist/main.js
🔧 Configuration
Environment Variables
The server requires the following environment variables:
# Required: Your Azure DevOps organization URL
AZURE_ORG_URL=https://dev.azure.com/yourorg
# Required: Your Azure DevOps Personal Access Token (PAT)
AZURE_PERSONAL_ACCESS_TOKEN=your_pat_here
Setting Environment Variables
Method 1: Direct Environment Variables
AZURE_ORG_URL=https://dev.azure.com/yourorg \
AZURE_PERSONAL_ACCESS_TOKEN=your_token \
npx -y @ahmedrowaihi/azure-mcp-fastmcp
Method 2: Using .env File
Create a .env file in your project root:
AZURE_ORG_URL=https://dev.azure.com/yourorg
AZURE_PERSONAL_ACCESS_TOKEN=your_token
Then run:
npx dotenv -e .env -- npx -y @ahmedrowaihi/azure-mcp-fastmcp
Method 3: System Environment Variables
Add to your shell profile (~/.bashrc, ~/.zshrc, etc.):
export AZURE_ORG_URL="https://dev.azure.com/yourorg"
export AZURE_PERSONAL_ACCESS_TOKEN="your_token"
🛠️ Available Tools
🔐 Azure DevOps Permissions
Your Personal Access Token (PAT) needs the following permissions:
- Code: Read (for repository access)
- Work Items: Read & Write (for work item management)
- Project and Team: Read (for project and team information)
- Policy: Read (for branch policy access)
🚀 Usage Examples
Basic Usage
# Start the MCP server
npx -y @ahmedrowaihi/azure-mcp-fastmcp
With MCP Client Configuration
If using an MCP client like Claude Desktop, add to your configuration:
{
"mcpServers": {
"azure-devops": {
"command": "npx",
"args": ["-y", "@ahmedrowaihi/azure-mcp-fastmcp"],
"env": {
"AZURE_ORG_URL": "https://dev.azure.com/yourorg",
"AZURE_PERSONAL_ACCESS_TOKEN": "your_token"
}
}
}
}
Bulk Create Work Items
{
"project": "MyProject",
"items": [
{
"type": "Epic",
"title": "Epic 1",
"children": [
{
"type": "Feature",
"title": "Feature A",
"children": [
{
"type": "User Story",
"title": "Story 1",
"children": [
{ "type": "Task", "title": "Task X" },
{ "type": "Task", "title": "Task Y" }
]
}
]
}
]
}
]
}
Assign Work Item to Iteration
{
"id": 12345,
"iterationId": "MyProject\\Iteration 1"
}
🛠️ Development
Prerequisites
- Bun (JavaScript runtime)
- Node.js 18+ (for compatibility)
Development Commands
# Install dependencies
bun install
# Build the project
bun run build
# Start development server
bun run dev
# Run the built server
bun run dist/main.js
Project Structure
├── azure/ # Azure DevOps services and connection
├── formatters/ # Data formatting utilities
├── mcp/ # MCP server and tools
├── dist/ # Built executable (generated)
├── main.ts # Entry point
└── package.json # Project configuration
📄 License
This project is licensed under the MIT License.
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
📞 Support
If you encounter any issues or have questions, please open an issue on GitHub.
Note: This MCP server is designed to be a standalone executable that doesn't require installing dependencies when used with npx. All dependencies are bundled into the final executable for optimal user experience.
⚠️ Known Issues
- Iteration Node Update Limitation: Updating project-level iteration node dates (start/end) via the Azure DevOps SDK fails with "Iteration node not found" even when the node is confirmed to exist and is fetchable by ID. All tested path formats fail for update/fetch by path, but fetching by ID works. This may be an SDK bug, REST/SOAP mismatch, or permissions issue. If you encounter this, consider using the Azure DevOps REST API directly or check for updates to the SDK.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。