经 AI Skill Hub 精选评估,Azure DevOps MCP 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
Azure DevOps MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Azure DevOps MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/viamus/mcp-azure-devops
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"azure-devops-mcp": {
"command": "npx",
"args": ["-y", "mcp-azure-devops"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Azure DevOps MCP 执行以下任务... Claude: [自动调用 Azure DevOps MCP MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"azure_devops_mcp": {
"command": "npx",
"args": ["-y", "mcp-azure-devops"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
A Model Context Protocol (MCP) server for Azure DevOps integration, enabling AI assistants to interact with Azure DevOps Work Items, Git Repositories, Pull Requests, and Pipelines.
Note: Flow metrics, WIP analysis, and other analytics features were removed. WithActivatedDateandClosedDatenow exposed on all work item queries, Claude can derive cycle time, lead time, aging, and throughput directly from the data — no pre-built analytics tools needed.
---
This project implements an MCP server that exposes tools for querying and managing Work Items and Git Repositories in Azure DevOps. It can be used with any compatible MCP client, such as Claude Desktop, Claude Code, or other assistants that support the protocol.
---
| Requirement | Version | Notes |
|---|---|---|
| [.NET SDK](https://dotnet.microsoft.com/download) | 10.0+ | Required for local development |
| [Docker](https://www.docker.com/) | Latest | Recommended for running |
| Azure DevOps Account | - | With Personal Access Token |
curl http://localhost:8080/health
For Windows users, a PowerShell script is available that automates the entire setup process:
```powershell
irm https://raw.githubusercontent.com/viamus/mcp-azure-devops/main/install-mcp-azure-devops.ps1 -OutFile install-mcp-azure-devops.ps1
.\install-mcp-azure-devops.ps1 ` -OrganizationUrl "https://dev.azure.com/your-organization" ` -PersonalAccessToken "your-pat-token" ` -DefaultProject "your-project-name" ` -ApiKey "your-secure-api-key" # Optional: enables API key authentication
The script will automatically:
- Install .NET 10 SDK (if not present)
- Install Node.js (if not present)
- Install Claude Code CLI (if not present)
- Clone the repository
- Configure your Azure DevOps credentials
- Register the MCP server with Claude Code (HTTPS transport)
For multiple organizations/PATs, run the installer for the primary organization, then add `AzureDevOps:Organizations` entries to `appsettings.json` or use the Docker environment variables from `.env.example`.
After installation, start the server:powershell cd $env:USERPROFILE\mcp-azure-devops dotnet run --project src/Viamus.Azure.Devops.Mcp.Server ```
---
| Tool | Description |
|---|---|
get_pipelines | Lists all pipelines (build definitions) in a project |
get_pipeline | Gets details of a specific pipeline by ID |
get_pipeline_runs | Gets recent runs (builds) for a specific pipeline |
get_build | Gets details of a specific build by ID |
get_builds | Lists builds with optional filters (status, result, branch, requester) |
get_build_logs | Gets the list of log files for a build |
get_build_log_content | Gets the content of a specific build log |
get_build_timeline | Gets the timeline (stages, jobs, tasks) for a build |
query_builds | Advanced query with multiple combined filters |
---
Best for: Production use, quick setup without .NET installed
1. Create your .env file from the template:
cp .env.example .env
# Edit .env with your Azure DevOps credentials
For multiple organizations/PATs, fill AZURE_DEVOPS_ORGANIZATION_0_*, AZURE_DEVOPS_ORGANIZATION_1_*, and AZURE_DEVOPS_DEFAULT_ORGANIZATION in .env.
2. Start the server:
docker compose up -d
Server URL: http://localhost:8080 (internal)
Important: For production, use a reverse proxy (nginx, traefik, or a cloud load balancer) in front of the container to provide HTTPS/TLS termination.
Useful commands:
docker compose logs -f # View logs
docker compose down # Stop the server
docker compose up -d --build # Rebuild and start
docker compose up -d
For Docker, add to your `.env` file (see `.env.example` for the full template):bash MCP_API_KEY=your-secret-api-key MCP_REQUIRE_API_KEY=true
#### How It Works
- When `RequireApiKey` is `false` (default): No authentication required
- When `RequireApiKey` is `true`: All requests (except `/health`) require a valid API key
- The `/health` endpoint is always accessible without authentication
#### Providing the API Key
Clients can provide the API key one way:
**Option 1 - X-API-Key Header (recommended):**bash curl -H "X-API-Key: your-secret-key" https://localhost:5001
#### Generating a Secure API Key
bash
---
#### PipelineDto Pipeline (build definition) details including Id, Name, Folder, ConfigurationType, and QueueStatus.
#### BuildDto Comprehensive build information including: - Id, BuildNumber, Status, Result - SourceBranch, SourceVersion - RequestedBy, RequestedFor - QueueTime, StartTime, FinishTime - Definition details, LogsUrl, Reason, Priority
#### BuildLogDto Build log metadata with Id, Type, Url, LineCount, and timestamps.
#### BuildTimelineRecordDto Timeline record (stage, job, or task) with Id, ParentId, Type, Name, State, Result, timing information, and error/warning counts.
---
```bash
dotnet build
dotnet build -c Release ```
Get up and running in 3 steps:
After configuring the MCP client, you can ask questions like:
git clone https://github.com/viamus/mcp-azure-devops.git
cd mcp-azure-devops
Option A — .env file (recommended for Docker):
```bash cp .env.example .env
**Option B — `appsettings.json` (for .NET CLI):**
Edit `src/Viamus.Azure.Devops.Mcp.Server/appsettings.json` with your Azure DevOps credentials:
json { "AzureDevOps": { "OrganizationUrl": "https://dev.azure.com/your-organization", "PersonalAccessToken": "your-personal-access-token", "DefaultProject": "your-project-name" } }
For multiple Azure DevOps organizations or PATs, keep one entry per organization and select it in tool calls with the optional `organization` argument:
json { "AzureDevOps": { "DefaultOrganization": "primary", "Organizations": [ { "Name": "primary", "OrganizationUrl": "https://dev.azure.com/primary-org", "PersonalAccessToken": "primary-pat", "DefaultProject": "primary-project" }, { "Name": "secondary", "OrganizationUrl": "https://dev.azure.com/secondary-org", "PersonalAccessToken": "secondary-pat", "DefaultProject": "secondary-project" } ] } } ```
Need a PAT? See Creating a Personal Access Token below.
Best for: Development, debugging
dotnet run --project src/Viamus.Azure.Devops.Mcp.Server
Server URL: http://localhost:5000
HTTPS Support: The server can also run with HTTPS on port 5001, but this may cause certificate validation issues with some MCP clients (e.g., Claude Code). If you need HTTPS locally, configure the development certificate properly:For production environments, use a reverse proxy with properly configured TLS certificates instead.> # Trust the development certificate (first time only) > dotnet dev-certs https --trust > > # Run with HTTPS > dotnet run --project src/Viamus.Azure.Devops.Mcp.Server --urls "https://localhost:5001" >
Best for: Deployment without .NET runtime
```bash
The server supports optional API key authentication to protect your MCP endpoints.
Add to appsettings.json:
{
"ServerSecurity": {
"ApiKey": "your-secret-api-key",
"RequireApiKey": true
}
}
Or via environment variables: ```bash
curl http://localhost:5000/health
curl -H "X-API-Key: your-key" http://localhost:5000 ``` </details>
<details> <summary><strong>Project not found</strong></summary>
1. Verify AZURE_DEVOPS_DEFAULT_PROJECT matches exact project name 2. Or pass the project name explicitly in your queries 3. Check the selected organization's PAT has access to the project </details>
<details> <summary><strong>Docker: Container exits immediately</strong></summary>
1. Check if appsettings.json has the required Azure DevOps configuration 2. View logs: docker compose logs 3. Ensure port 8080 is not in use by another application </details>
<details> <summary><strong>.NET CLI: dotnet run fails</strong></summary>
1. Verify .NET 10 SDK is installed: dotnet --version 2. Restore packages: dotnet restore 3. Check if appsettings.json has the correct Azure DevOps settings </details>
---
本项目实现了一个 MCP Server,旨在为 Azure DevOps 提供强大的扩展能力。通过该服务,开发者可以利用 MCP 协议将 Azure DevOps 中的 Work Items(工作项)查询与管理功能,以及 Git Repositories(代码仓库)的操作能力,无缝集成到任何兼容 MCP 协议的客户端中,例如 Claude Desktop、Claude Code 或其他 AI 助手,从而实现通过自然语言驱动 DevOps 工作流。
在开始使用前,请确保您的开发环境已满足以下要求:本地开发需要安装 .NET SDK 10.0 或更高版本;若希望通过容器化方式运行,建议安装最新版本的 Docker;此外,您需要拥有 Azure DevOps 的访问权限,并准备好相应的 Personal Access Token (PAT) 以进行身份验证。
本项目支持多种安装方式。对于 Docker 用户,可以直接通过容器运行;对于 Windows 用户,官方提供了一个 PowerShell 自动化安装脚本,您只需以管理员权限运行该脚本,并传入 OrganizationUrl、PersonalAccessToken 及 DefaultProject 等必要参数,即可完成全自动化的环境配置与部署。
快速上手只需简单三步:首先克隆项目仓库,随后根据您的运行环境(Docker 或 .NET CLI)进行配置,最后启动服务。配置完成后,您可以在支持 MCP 的客户端中直接通过自然语言向 AI 提问,例如查询特定的工作项或管理代码仓库,AI 将通过该 MCP Server 调用 Azure DevOps API 来执行任务。
配置过程取决于您的运行模式。若使用 Docker,推荐通过编辑 `.env` 文件来配置 Azure DevOps 的凭据;若使用 .NET CLI 运行,则需修改 `src/Viamus.Azure.Devops.Mcp.Server/appsettings.json` 文件。请务必确保 OrganizationUrl、PersonalAccessToken 和 DefaultProject 等关键参数准确无误。
为了增强安全性,本服务器支持可选的 API Key 身份验证机制。您可以通过在 `appsettings.json` 中设置 `RequireApiKey` 为 `true` 并提供 `ApiKey`,或者通过环境变量来启用此功能。在测试时,可以通过访问 `/health` 端点验证服务状态,并在请求头中携带 `X-API-Key` 来测试受保护的接口。
在使用过程中,如果遇到“Project not found”错误,请首先检查 `AZURE_DEVOPS_DEFAULT_PROJECT` 是否与 Azure DevOps 中的项目名称完全一致;其次,确保您的 PAT 令牌拥有访问该项目的权限;此外,您也可以尝试在查询时显式传递项目名称以规避默认配置问题。
高质量的MCP工具,支持Azure DevOps自动化
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:Azure DevOps MCP 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | mcp-azure-devops |
| 原始描述 | 开源MCP工具:Azure DevOps MCP for querying repositories, pipelines, work items, and delivery 。⭐8 · C# |
| Topics | azure-devopsmcpc# |
| GitHub | https://github.com/viamus/mcp-azure-devops |
| License | MIT |
| 语言 | C# |
收录时间:2026-05-29 · 更新时间:2026-05-30 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端