mcp-for-azure-devops-boards

mcp-for-azure-devops-boards

MCP for Azure DevOps Boards is a MCP server that lets your favourite AI browse, query and update Azure DevOps work items as if it were a project manager. Written in Rust and optimized for tokens usagem, It runs via stdio or HTTP mode and uses standard Azure authentication with az login.

Category
访问服务器

README

MCP for Azure DevOps Boards

CI - PR - Build & Test CD - Tag - Build & Release

<a href="https://glama.ai/mcp/servers/@danielealbano/mcp-for-azure-devops"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@danielealbano/mcp-for-azure-devops/badge" /> </a>

A Model Context Protocol (MCP) server for interacting with Azure DevOps Boards and Work Items, written in Rust.

Features

  • Work Item Management: Create, update, get, and query work items.

  • Board Integration: List teams, boards, and fetch board items.

  • WIQL Support: Run custom WIQL queries.

  • Simplified Output: Optimized JSON output for LLM consumption (reduced token usage).

Installation

Check out the section MCP Configuration for how to configure your preferred AI (MCP) client.

macOS (Homebrew)

brew tap danielealbano/mcp-tools
brew install mcp-for-azure-devops-boards

The path to the binary will be /opt/homebrew/bin/mcp-for-azure-devops-boards.

Windows (Scoop)

scoop bucket add mcp-tools https://github.com/danielealbano/scoop-mcp-tools
scoop install mcp-for-azure-devops-boards

The path to the binary will be %USERPROFILE%\scoop\apps\mcp-for-azure-devops-boards\current\mcp-for-azure-devops-boards.exe.

Configuration

Setting Description CLI Flag Env Variable
Server Mode Run as HTTP server instead of stdio --server N/A
Port Port for HTTP server (default: 3000) --port N/A

Note: If --server is not specified, the software will run in stdio mode.

Authentication

This server leverages standard Azure authentication mechanisms (like az or azd) to query Azure DevOps.

Installing Azure CLI

If you don't have the Azure CLI installed:

macOS (Homebrew):

brew install azure-cli

Windows (Scoop):

scoop install azure-cli

Windows (Chocolatey):

choco install azure-cli

For other installation methods, see the official Azure CLI installation guide.

Logging In

To authenticate, run:

az login

Usage

Stdio Mode (Default)

This is the standard mode for MCP clients (like Claude Desktop or Cursor). This mode is preferred for security as it ensures no credentials are shared over the network.

path/to/mcp-for-azure-devops-boards

HTTP Server Mode

You can also run it as an HTTP server (SSE). Note that in this mode, the server listens on 0.0.0.0 (all interfaces).

path/to/mcp-for-azure-devops-boards --server --port 3000

MCP Configuration

Note: Make sure you have run az login in your terminal so the process can pick up the credentials.

Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "azure-devops-boards": {
      "command": "path/to/mcp-for-azure-devops-boards"
    }
  }
}

Available Tools

This software is currently in development. The tools and their parameters are subject to change.

The server exposes the following tools for MCP clients.

The general structure of the tool names is azdo_VERB_WHAT (e.g., azdo_list_teams, azdo_get_work_item).

Discovery

  • azdo_list_organizations: List all Azure DevOps organizations the authenticated user has access to.
    • Required: None (uses authenticated user's credentials)
  • azdo_list_projects: List all projects in an Azure DevOps organization.
    • Required: organization

Work Items

Note: All work item tools require organization and project parameters.

  • azdo_create_work_item: Create a new work item.
    • Required: organization, project, work_item_type, title
    • Optional: description, assigned_to, area_path, iteration_path, state, board_column, board_row, priority, severity, story_points, effort, remaining_work, tags, activity, parent_id, start_date, target_date, acceptance_criteria, repro_steps, fields (JSON string for custom fields).
  • azdo_update_work_item: Update an existing work item.
    • Required: organization, project, id
    • Optional: All fields available in creation.
  • azdo_get_work_item: Get details of a specific work item.
    • Required: organization, project, id
    • Optional: include_latest_n_comments (number of recent comments to include, -1 for all)
  • azdo_get_work_items: Get multiple work items by their IDs.
    • Required: organization, project, ids (array of work item IDs)
    • Optional: include_latest_n_comments (number of recent comments to include, -1 for all)
  • azdo_query_work_items: Query work items using structured filters.
    • Required: organization, project
    • Optional Filters: area_path, iteration_path, created_date_from/to, modified_date_from/to.
    • Inclusion Lists: include_board_column, include_board_row, include_work_item_type, include_state, include_assigned_to, include_tags.
    • Exclusion Lists: exclude_board_column, exclude_board_row, exclude_work_item_type, exclude_state, exclude_assigned_to, exclude_tags.
    • Optional: include_latest_n_comments (number of recent comments to include, -1 for all)
  • azdo_query_work_items_by_wiql: Execute a raw WIQL (Work Item Query Language) query.
    • Required: organization, project, query
    • Optional: include_latest_n_comments (number of recent comments to include, -1 for all)
  • azdo_add_comment: Add a comment to a work item.
    • Required: organization, project, work_item_id, text
  • azdo_link_work_items: Create a relationship between two work items.
    • Required: organization, project, source_id, target_id, link_type (Parent, Child, Related, Duplicate, Dependency).

Boards & Teams

Note: All board and team tools require organization and project parameters.

  • azdo_list_teams: List all teams in the project.
    • Required: organization, project
  • azdo_get_team: Get details of a specific team.
    • Required: organization, project, team_id
  • azdo_list_team_boards: List boards for a specific team.
    • Required: organization, project, team_id
  • azdo_get_team_board: Get details of a specific board.
    • Required: organization, project, team_id, board_id
  • azdo_list_work_item_types: List all available work item types in the project.
    • Required: organization, project
  • azdo_list_tags: List all tags in use in the project.
    • Required: organization, project
  • azdo_get_team_current_iteration: Get the current active iteration/sprint for a team.
    • Required: organization, project, team_id
  • azdo_get_team_iterations: Get all iterations/sprints for a team.
    • Required: organization, project, team_id

Contributing

We welcome contributions!

  1. Fork the repository.
  2. Create a new branch for your feature or bugfix (git checkout -b feature/amazing-feature).
  3. Commit your changes.
  4. Push to your branch.
  5. Open a Pull Request.

Building from Source

Prerequisites

  • Rust (latest stable version)
  • Azure CLI (required for local authentication)

Steps

  1. Clone the repository:

    git clone https://github.com/danielealbano/mcp-for-azure-devops-boards.git
    cd mcp-for-azure-devops-boards
    
  2. Build the project:

    cargo build --release
    

Tooling

  • Run tests: cargo test
  • Check code style: cargo fmt --check
  • Linting: cargo clippy

Disclaimer

This project is not affiliated with, endorsed by, or sponsored by Microsoft. Azure, Azure DevOps, and related trademarks are the property of their respective owners. This software uses standard Microsoft's services APIs to interact with Azure and Microsoft Graph, among other services.

License

This project is licensed under the MIT License - see the LICENSE.md file for details.

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