Azure DevOps MCP Server
Enables reading and updating Azure DevOps work items, comments, metadata, and relations from an MCP-compatible client.
README
Azure DevOps MCP Server
Azure DevOps MCP server for reading and updating work items, comments, metadata, and relations from an MCP-compatible client.
Features
- Read one or many work items by ID
- Query work items with raw WIQL
- List work items with structured filters such as type, state, assignee, tags, iteration, and area path
- Create, update, bulk update, and delete work items
- Read and add work item comments
- Read, add, and remove work item relations
- List projects, work item types, iterations, and area paths
- Expose reusable prompts for sprint summaries, bug triage, and drafting work items
- Expose MCP resources for server info and individual work items
- Support
stdioand HTTP transport modes - Support interactive Azure sign-in with persistent token caching
- Support PAT-based auth and Azure Key Vault backed secret loading
Requirements
- Node.js 20 or newer
- Access to an Azure DevOps organization and project
- An MCP client that supports a JSON server configuration
Install
npm install
npm run build
Authentication
The server supports these authentication modes:
interactive: opens the Microsoft sign-in flow on first use, then reuses the cached session on later runsdefault: uses the Azure default credential chainAZURE_DEVOPS_PAT: uses a personal access token if you prefer PAT-based auth
For interactive auth, the server stores:
- an authentication record at
~/.azure-devops-mcp/authentication-record.json - a persistent token cache managed by the operating system
Configuration
The server reads configuration from:
- environment variables
- an optional
mcp-config.jsonfile in the project root
If both are present, environment variables take precedence.
Common settings
| Setting | Description |
|---|---|
AZURE_DEVOPS_ORG_URL |
Azure DevOps organization URL |
AZURE_DEVOPS_DEFAULT_PROJECT |
Default project used when a tool call omits project |
AZURE_AUTH_MODE |
interactive or default |
AZURE_AUTH_RECORD_PATH |
Optional custom path for the auth record file |
AZURE_DEVOPS_PAT |
Optional PAT for direct Azure DevOps auth |
AZURE_CLIENT_ID |
Optional Entra app client ID |
AZURE_TENANT_ID |
Optional Entra tenant ID |
AZURE_CLIENT_SECRET |
Optional client secret for non-interactive Azure auth |
AZURE_KEYVAULT_URI |
Optional Key Vault URI for loading secrets |
MCP_TRANSPORT |
stdio or http |
MCP_HTTP_HOST |
HTTP bind host when using HTTP transport |
MCP_HTTP_PORT |
HTTP port when using HTTP transport |
MCP_AUTH_TOKEN |
Optional bearer token for the HTTP /mcp endpoint |
MCP_TLS_CERT |
Optional TLS certificate secret or path value |
MCP_TLS_KEY |
Optional TLS private key secret or path value |
LOG_LEVEL |
Log level such as info or debug |
REQUEST_TIMEOUT_MS |
Per-request timeout in milliseconds |
BULK_REQUEST_TIMEOUT_MS |
Timeout for bulk requests in milliseconds |
MAX_RETRY_ATTEMPTS |
Retry count for transient failures |
Example mcp-config.json
{
"azureDevopsOrgUrl": "https://dev.azure.com/example-org",
"azureDevopsDefaultProject": "example-project",
"azureAuthMode": "interactive",
"mcpTransport": "stdio",
"logLevel": "info",
"requestTimeoutMs": 10000,
"bulkRequestTimeoutMs": 30000,
"maxRetryAttempts": 3
}
MCP Client JSON Config
Stdio example
Use this when your MCP client launches the server as a local process.
{
"mcpServers": {
"azure-devops": {
"command": "node",
"args": [
"F:/path/to/azure-mcp/dist/index.js"
],
"env": {
"AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/example-org",
"AZURE_DEVOPS_DEFAULT_PROJECT": "example-project",
"AZURE_AUTH_MODE": "interactive",
"MCP_TRANSPORT": "stdio",
"LOG_LEVEL": "info"
}
}
}
}
HTTP example
Use this when you want to run the server separately and expose /mcp over HTTP.
Server environment:
{
"AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/example-org",
"AZURE_DEVOPS_DEFAULT_PROJECT": "example-project",
"AZURE_AUTH_MODE": "interactive",
"MCP_TRANSPORT": "http",
"MCP_HTTP_HOST": "127.0.0.1",
"MCP_HTTP_PORT": "3000",
"MCP_AUTH_TOKEN": "replace-with-a-demo-token"
}
Client connection example:
{
"mcpServers": {
"azure-devops-http": {
"transport": {
"type": "streamable-http",
"url": "http://127.0.0.1:3000/mcp",
"headers": {
"Authorization": "Bearer replace-with-a-demo-token"
}
}
}
}
}
Available Tools
get_work_itemget_work_itemsquery_work_itemslist_work_itemscreate_work_itemupdate_work_itembulk_update_work_itemsdelete_work_itemget_commentsadd_commentget_relationsadd_relationremove_relationlist_projectslist_work_item_typeslist_iterationslist_area_paths
Available Prompts
summarize_sprinttriage_bugsdraft_work_item
Available Resources
azure-devops://server/infoazure-devops://{organization}/{project}/workitems/{id}
Run
Development mode:
npm run dev
Production build:
npm run build
npm start
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。