Azure DevOps

MCP开发工具

提供方 未标注

开发工具 HTTP · 远程 未标注 社区 / 第三方 Claude DesktopClaudeCursorVS Code
查看接入方式

Provides comprehensive integration with Azure DevOps services. Browse Azure DevOps MCP Server for Claude, Cursor, VS Code, and other AI agents.

一句话选型结论

按资料字段整理

Azure DevOps 属于开发工具类 MCP 服务器,HTTP · 远程,鉴权方式未标注,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接复制的远程端点配置。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类开发工具 传输方式HTTP · 远程 鉴权未标注 部署方式远程部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

开发工具
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

Development

安装与配置

HTTP · 远程 未标注
连远程 HTTPS 端点,通常为 Streamable HTTP
# Build the Docker image docker build -t azuredevops-mcp . # Run the container with environment variables docker run -it \ -e AzureDevOps__OrganizationUrl="https://dev.azure.com/your-organization" \ -e AzureDevOps__PersonalAccessToken="your-pat-goes-here" \ azuredevops-mcp

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    确认你的客户端支持远程端点,并拿到服务地址。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
代码与仓库操作

在对话里直接查代码、提 issue、走 PR,省掉来回切工具。

本地命令与脚本

把构建、测试、格式化这类重复命令交给模型执行。

接口联调与测试

让模型调你的接口、跑一遍用例,快速定位问题。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • 远程端点依赖网络与服务方可用性,注意密钥与调用额度。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在开发工具场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Azure DevOps当前 未标注 HTTP · 远程 远程部署 有 未标注
Git 838e2ec1 12 stdio · 本地进程 本地部署 有 2026-05-17
Markitdown MCP 2c653a5f 1 stdio · 本地进程 本地部署 有 2026-05-17
JavaGuide 未标注 stdio · 本地进程 本地部署 有 2026-04-11
awesome-claude-skills 未标注 stdio · 本地进程 本地部署 有 2026-04-26
Context7 831acf40 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

开发工具
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类开发工具本站按上游分类展示
连接方式HTTP · 远程连远程 HTTPS 端点,通常为 Streamable HTTP
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型远程部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

13.7 KB
来自项目仓库与上游目录的原文,未做删改

Azure DevOps MCP Server

A Model Context Protocol (MCP) server that provides comprehensive integration with Azure DevOps. This server enables AI assistants like Claude Desktop and development tools like VS Code to seamlessly interact with Azure DevOps through the MCP protocol using stdio transport.

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details on how to get started.

  • 🐛 Report bugs
  • 💡 Request features
  • 📖 Improve documentation

Features

  • Projects: Browse Azure DevOps projects and team information
  • Repositories: View repositories, files, commits, branches, and pull requests
  • Work Items: Query and manage work items with optional write operations
  • Performance Monitoring: Built-in performance tracking and optimization
  • Production Ready: Comprehensive caching, error handling, and security features
  • Safe Write Operations: Opt-in write capabilities with audit logging

Available MCP Tools

The server exposes Azure DevOps functionality through specialized tool categories:

Core Azure DevOps Tools (AzureDevOpsTools)

Read-Only Operations (Always Available):
- list_projects - Lists all projects in the Azure DevOps organization
- list_repositories - Lists repositories in a specific project
- list_repository_items - Lists files and folders in a repository path
- get_file_content - Gets the content of a specific file from a repository
- list_work_items - Lists work items in a specific project
- get_work_item - Gets detailed information about a specific work item

Safe Write Tools (SafeWriteTools)

Write Operations (Require Explicit Opt-In):
- add_pull_request_comment - Adds a comment to a pull request (requires PullRequestComments)
- create_draft_pull_request - Creates a draft pull request (requires CreateDraftPullRequest)
- update_work_item_tags - Adds or removes tags from work items (requires UpdateWorkItemTags)

Batch Operations (BatchTools)

High-Performance Bulk Operations:
- batch_get_work_items - Retrieves multiple work items efficiently in parallel
- batch_get_repositories - Gets multiple repository details in parallel

Test Plan Management (TestPlanTools)

Test Management Operations:
- get_test_plans - Gets test plans for a specific Azure DevOps project
- get_test_plan - Gets detailed information about a specific test plan
- get_test_suites - Gets test suites for a specific test plan
- get_test_runs - Gets test runs for a specific Azure DevOps project
- get_test_run - Gets detailed information about a specific test run
- get_test_results - Gets test results for a specific test run

Performance & Monitoring (PerformanceTools)

System Management:
- get_performance_metrics - View operation timings, API call statistics, and cache performance
- get_cache_statistics - Detailed cache performance and hit rate statistics
- clear_cache - Clear all cached data to force fresh API calls

Prerequisites

  • .NET 9 SDK (for local development)
  • Docker (for running the container)
  • Azure DevOps account with appropriate permissions

🚀 Quick Development Setup

Option 1: Development Containers (Recommended)

Get started in seconds with a fully configured development environment:

VS Code:
1. Install VS Code and the Dev Containers extension
2. Clone this repository and open in VS Code
3. Click "Reopen in Container" when prompted
4. Start coding immediately with .NET 9, tools, and extensions pre-configured!

Having issues? See .devcontainer/README.md for troubleshooting

GitHub Codespaces:
1. Click the "Code" button on this repository
2. Select "Codespaces" → "Create codespace on main"
3. Develop directly in your browser with zero setup

Option 2: Local Development

For traditional local development:```bash

Manual setup (any platform)

dotnet restore && dotnet build && dotnet test


## Getting Started

### Generating an Azure DevOps Personal Access Token (PAT)

1. Sign in to your Azure DevOps organization ()
2. Click on your profile icon in the top right corner
3. Select **Personal access tokens** from the dropdown menu
4. Click **+ New Token**
5. Name your token (e.g., "MCP Server Access")
6. Select the appropriate organization where you want to use the token
7. For read-only access, select the following scopes:
   - **Code**: Read
   - **Work Items**: Read
   - **Project and Team**: Read
   - **Test Management**: Read (for test plan operations)
8. Set an expiration date for your token
9. Click **Create**
10. **Copy and securely store your token** (you won't be able to see it again!)

### Running the MCP Server with Docker```bash
# Build the Docker image
docker build -t azuredevops-mcp .

# Run the container with environment variables
docker run -it \
  -e AzureDevOps__OrganizationUrl="https://dev.azure.com/your-organization" \
  -e AzureDevOps__PersonalAccessToken="your-pat-goes-here" \
  azuredevops-mcp

Running from Source```bash

Set environment variables

$env:AzureDevOps__OrganizationUrl="https://dev.azure.com/your-organization"
$env:AzureDevOps__PersonalAccessToken="your-pat-goes-here"

Build and run

dotnet restore
dotnet build
dotnet run --project src/AzureDevOps.MCP


### Connecting to the MCP Server

The server uses stdio transport, which means it communicates via standard input/output. This is the standard way MCP servers are integrated with tools like Claude Desktop, VS Code extensions, or other MCP clients.

For Claude Desktop, add this to your MCP configuration:```json
{
  "mcpServers": {
    "azure-devops": {
      "command": "docker",
      "args": [
        "run", "-i",
        "-e", "AzureDevOps__OrganizationUrl=https://dev.azure.com/your-organization",
        "-e", "AzureDevOps__PersonalAccessToken=your-pat-goes-here",
        "azuredevops-mcp"
      ]
    }
  }
}

Configuration

The server supports comprehensive configuration through environment variables or appsettings.json:

Required Configuration

Setting Description Required
AzureDevOps__OrganizationUrl Your Azure DevOps organization URL (e.g., https://dev.azure.com/myorg) Yes
AzureDevOps__PersonalAccessToken Your Azure DevOps Personal Access Token Yes

Optional Configuration

Setting Description Default
AzureDevOps__EnabledWriteOperations Array of enabled write operations []
AzureDevOps__RequireConfirmation Require explicit confirmation for write operations true
AzureDevOps__EnableAuditLogging Enable audit logging for all operations true

Advanced Configuration

The server supports extensive production configuration options:```json
{
"AzureDevOps": {
"OrganizationUrl": "https://dev.azure.com/your-organization",
"PersonalAccessToken": "your-pat-goes-here",
"EnabledWriteOperations": ["PullRequestComments"],
"RequireConfirmation": true,
"EnableAuditLogging": true,
"Monitoring": {
"EnablePerformanceTracking": true,
"EnableErrorTracking": true,
"Sentry": {
"Dsn": "your-sentry-dsn"
}
}
},
"Caching": {
"EnableMemoryCache": true,
"MaxMemoryCacheSizeMB": 100,
"DefaultCacheDurationMinutes": 15
},
"Performance": {
"SlowOperationThresholdMs": 1000,
"EnableCircuitBreaker": true,
"EnableMonitoring": true
},
"Security": {
"EnableKeyVault": false,
"KeyVaultUrl": "https://your-keyvault.vault.azure.net/"
},
"RateLimiting": {
"EnableRateLimiting": true,
"RequestsPerMinute": 60,
"RequestsPerHour": 1000
}
}


### Available Write Operations

Enable specific write operations by adding them to `EnabledWriteOperations`:

- `PullRequestComments` - Add comments to pull requests
- `WorkItemComments` - Add comments to work items
- `CreateDraftPullRequest` - Create draft pull requests (not published until ready)
- `UpdateWorkItemTags` - Add or remove tags from work items

### Write Operation Safety Features

1. **Opt-In by Default**: All write operations are disabled unless explicitly enabled
2. **Confirmation Required**: Write operations require a `confirm: true` parameter (can be disabled)
3. **Audit Logging**: All write operations are logged with timestamp, operation type, and result
4. **Preview Mode**: Operations show what will be changed before confirmation

## Architecture

This project implements a modern, production-ready architecture with .NET 9:

### Core Architecture Layers

- **MCP Tools Layer** (`Tools/`): Five specialized tool categories implementing MCP protocol
  - `AzureDevOpsTools` - Core read operations
  - `SafeWriteTools` - Opt-in write operations with safety measures
  - `BatchTools` - High-performance bulk operations
  - `TestPlanTools` - Test plan and test management operations
  - `PerformanceTools` - System monitoring and management

- **Services Layer** (`Services/`):
  - **Core Services** (`Core/`): Domain-specific business logic (Projects, Repositories, WorkItems, Builds, Tests, Search)
  - **Infrastructure Services** (`Infrastructure/`): Cross-cutting concerns (Caching, Performance, Health, Connection Management)
  - **Legacy Service**: `AzureDevOpsService` for backward compatibility

- **Configuration Layer** (`Configuration/`): Modular configuration classes
  - `ProductionConfiguration` - Complete production settings
  - `CachingConfiguration` - Cache management
  - `PerformanceConfiguration` - Performance tuning
  - `SecurityConfiguration` - Security settings
  - `RateLimitingConfiguration` - API rate limiting

- **Security & Infrastructure**:
  - **Authorization** (`Authorization/`): Permission-based access control
  - **Security** (`Security/`): Secret management with Azure Key Vault support
  - **Error Handling** (`ErrorHandling/`): Resilient execution patterns

### Production Features

- **Performance Optimization**: Built-in caching, connection pooling, and performance monitoring
- **Reliability**: Circuit breaker patterns, retry policies, and health checks
- **Security**: Comprehensive secret management, authorization, and audit logging
- **Monitoring**: Sentry integration, structured logging, and performance metrics
- **Scalability**: Rate limiting, memory management, and efficient batch operations

## Building from Source```bash
# Restore packages
dotnet restore

# Build the project
dotnet build

# Run the application
dotnet run --project src/AzureDevOps.MCP

Development

Technology Stack

  • .NET 9: Latest framework with modern C# features
  • ModelContextProtocol: MCP SDK for protocol implementation
  • Azure DevOps Client Libraries: Official Microsoft libraries for Azure DevOps integration
  • BenchmarkDotNet: Performance benchmarking and optimization
  • Centralized Package Management: All package versions managed in Directory.Packages.props

Testing

The project includes comprehensive testing infrastructure:```bash

Run all tests (153 passing, 7 skipped, 160 total)

dotnet test

Run tests with coverage

./scripts/test-coverage.ps1

Run performance benchmarks

cd tests/AzureDevOps.MCP.Tests
dotnet run --configuration Release -- cache # Cache performance
dotnet run --configuration Release -- performance # Service performance
dotnet run --configuration Release -- config # Configuration benchmarks
dotnet run --configuration Release -- frozen # .NET 9 collections performance
```

Development Scripts

  • ./scripts/dev-setup.ps1 - Quick setup for new developers
  • ./scripts/test-coverage.ps1 - Run tests with coverage analysis
  • ./scripts/test-coverage.ps1 -OpenReport - Generate and open coverage report

Example Workflow: Test Plan → Clone → Tests → PR

The Azure DevOps MCP server enables powerful workflows for test-driven development:

Complete End-to-End Workflow

  1. Get Test Plan Requirementsbash # Use MCP client to get test plan details get_test_plans projectName="MyProject" get_test_plan projectName="MyProject" planId=123 get_test_suites projectName="MyProject" planId=123

  2. Get Repository Informationbash # Get repository details and clone URL list_repositories projectName="MyProject" list_repository_items projectName="MyProject" repositoryId="repo-guid" path="/"

  3. Local Development (You handle these steps)```bash
    # Clone repository using information from MCP server
    git clone https://dev.azure.com/org/project/_git/repository
    cd repository

# Create feature branch
git checkout -b feature/implement-test-plan-123

# Generate unit tests and UI tests based on test plan requirements
# (Use test plan details to understand what needs to be tested)

# Commit your changes
git add .
git commit -m "Implement tests for test plan #123"
git push origin feature/implement-test-plan-123
```

  1. Create Pull Requestbash # Use MCP server to create draft PR create_draft_pull_request projectName="MyProject" repositoryId="repo-guid" \ sourceBranch="feature/implement-test-plan-123" \ targetBranch="main" \ title="Implement tests for test plan #123" \ description="Added unit tests and UI tests based on test plan requirements" \ confirm=true

This workflow demonstrates how the MCP server bridges the gap between Azure DevOps test management and local development, enabling seamless test-driven development processes.

Security Notes

  • The PAT token should be kept secure and have minimal required permissions
  • By default, the server only performs read operations on Azure DevOps
  • Write operations must be explicitly enabled and are limited to safe operations
  • All write operations are audited and logged
  • Use environment variables for sensitive configuration
  • Audit logs are stored locally in the audit/ directory

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Azure DevOps 怎么安装?

在客户端按下面的安装命令接入:# Build the Docker image docker build -t azuredevops-mcp . # Run the container with environment variables docker run -it \ -e AzureDevOps__OrganizationUrl="https://dev.azure.com/your-organization" \ -e AzureDevOps__PersonalAccessToken="your-pat-goes-here" \ azuredevops-mcp。装完在客户端配置里引用同一个包或端点。

Azure DevOps 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是HTTP · 远程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Azure DevOps 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Azure DevOps 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Azure DevOps 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、VS Code、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Azure DevOps 能提供哪些能力?

资料显示能力标签包括 Development。具体工具清单以官方文档为准。

Azure DevOps 需要什么运行环境?

属于远程端点,不需要在本地装运行时。

Azure DevOps 是本地还是远程?

它是远程端点,连服务地址即可。传输方式为HTTP · 远程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。