Azure DevOps MCP Server
Enables AI assistants to search, create, update, and manage work items in Azure DevOps using natural language.
README
Azure DevOps MCP Server
MCP (Model Context Protocol) server for Azure DevOps Work Item Tracking integration. Enables AI assistants like Claude to search, create, update, and manage work items in Azure DevOps.
Features
- Search Work Items: Query using WIQL (Work Item Query Language)
- Get Work Item: Retrieve detailed work item information by ID
- Create Work Item: Create Bugs, Tasks, User Stories, Features, etc.
- Update Work Item: Modify fields, change state, update assignments
- Add Comments: Add discussion comments to work items
Installation
npm install @bugzy-ai/azure-devops-mcp-server
Or run directly with npx:
npx @bugzy-ai/azure-devops-mcp-server
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
AZURE_DEVOPS_ORG_URL |
Yes | Organization URL (e.g., https://dev.azure.com/myorg) |
AZURE_DEVOPS_PAT |
Yes | Personal Access Token |
AZURE_DEVOPS_MCP_DEBUG |
No | Enable debug logging to .azure-devops-mcp/mcp.log |
Note: Project name is specified per-request, not via environment variable. The AI agent discovers the project from context (e.g.,
.bugzy/runtime/project-context.md) or usesazuredevops_list_projectsto find available projects.
Creating a Personal Access Token (PAT)
- Go to Azure DevOps → User Settings → Personal Access Tokens
- Click "New Token"
- Set the required scopes:
vso.work- Read work itemsvso.work_write- Create and update work items
- Copy the token and set it as
AZURE_DEVOPS_PAT
MCP Configuration
Add to your MCP configuration file (e.g., claude_desktop_config.json):
{
"mcpServers": {
"azure-devops": {
"command": "npx",
"args": ["@bugzy-ai/azure-devops-mcp-server"],
"env": {
"AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/your-org",
"AZURE_DEVOPS_PAT": "your-pat-token"
}
}
}
}
Tools
azuredevops_list_projects
List all projects in the Azure DevOps organization. Use this to discover available projects.
{
top?: number, // Max projects to return (default: 100, max: 100)
skip?: number // Number to skip for pagination (default: 0)
}
azuredevops_search_work_items
Search for work items using WIQL queries.
{
project: string, // Azure DevOps project name (required)
wiql: string, // WIQL query
maxResults?: number // Max results (default: 50, max: 200)
}
Example WIQL queries:
-- Find open bugs
SELECT [System.Id], [System.Title], [System.State]
FROM WorkItems
WHERE [System.WorkItemType] = 'Bug'
AND [System.State] <> 'Closed'
ORDER BY [System.CreatedDate] DESC
-- Find work items assigned to me
SELECT [System.Id], [System.Title]
FROM WorkItems
WHERE [System.AssignedTo] = @Me
AND [System.State] = 'Active'
-- Find recent items in a specific area
SELECT [System.Id], [System.Title], [System.WorkItemType]
FROM WorkItems
WHERE [System.AreaPath] UNDER 'Project\Team'
AND [System.CreatedDate] >= @Today - 7
azuredevops_get_work_item
Get detailed information about a work item.
{
project: string, // Azure DevOps project name (required)
id: number, // Work item ID
fields?: string[], // Specific fields to retrieve
expand?: "None" | "Relations" | "Fields" | "Links" | "All"
}
azuredevops_create_work_item
Create a new work item.
{
project: string, // Azure DevOps project name (required)
type: string, // "Bug", "Task", "User Story", etc.
title: string, // Work item title
description?: string, // Description (HTML supported)
areaPath?: string, // Area path
iterationPath?: string,// Iteration/sprint path
assignedTo?: string, // User email or display name
priority?: number, // 1-4 (1=Critical, 4=Low)
severity?: string, // For bugs: "1 - Critical", "2 - High", etc.
tags?: string, // Semicolon-separated tags
parentId?: number // Parent work item ID
}
azuredevops_update_work_item
Update an existing work item using JSON Patch operations.
{
project: string, // Azure DevOps project name (required)
id: number,
operations: Array<{
op: "add" | "remove" | "replace",
path: string, // e.g., "/fields/System.State"
value?: any
}>
}
Example - Change state to Active:
{
"id": 123,
"operations": [
{ "op": "replace", "path": "/fields/System.State", "value": "Active" }
]
}
azuredevops_add_comment
Add a comment to a work item.
{
project: string, // Azure DevOps project name (required)
id: number, // Work item ID
text: string // Comment text (HTML supported)
}
Development
# Install dependencies
npm install
# Build
npm run build
# Run with MCP Inspector (for testing)
npm run dev
# Watch mode
npm run build:watch
Debugging
Enable debug logging by setting AZURE_DEVOPS_MCP_DEBUG=true. Logs are written to .azure-devops-mcp/mcp.log.
License
MIT
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。