MCP DevOps Plan Server
Enables work item management in DevOps Plan systems, allowing users to create, retrieve, filter, and delete work items, as well as manage applications, projects, components, and work item types through natural language.
README
MCP DevOps Plan Server
A Model Context Protocol (MCP) server implementation for DevOps Plan, enabling work item management through standardized MCP clients.
Features
- Retrieve applications and projects from Plan
- Get available components and work item types
- Create, retrieve, and delete work items
- Filter work items by type and owner
Warranties
This MCP server is provided "as is" without any warranties. It is designed to work with the DevOps Plan system and may require specific configurations to function correctly. Users are responsible for ensuring compatibility with their Plan instance. This server provides data destructive functionality, the author is not liable for any data loss due to use of this MCP capability.
Example Use Cases
1. Setting Up a New Project Sprint
Scenario: You're a project manager starting a new sprint and need to create multiple work items for your team.
Steps:
- "Get me all available applications in Plan"
- "Show me the projects in the 'WebApp Development' application"
- "What work item types are available in the 'Customer Portal' project?"
- "Create a new Epic titled 'User Authentication System' in the Customer Portal project"
- "Create three tasks: 'Design login UI', 'Implement OAuth integration', and 'Add password reset functionality'"
Benefits: Quickly set up organized work items for sprint planning and team assignment.
2. Sprint Review and Cleanup
Scenario: At the end of a sprint, you need to review completed work and clean up obsolete items.
Steps:
- "Show me all work items in the 'Mobile App' project"
- "Filter work items by type 'Bug' to see what issues were resolved"
- "Show me work items assigned to 'john.doe' to review his contributions"
- "Delete the work item with ID '12345' as it's no longer relevant"
- "Create a summary report of completed vs remaining work items"
Benefits: Maintain clean project state and generate insights for retrospectives.
3. Cross-Team Dependency Management
Scenario: You're coordinating between frontend and backend teams and need to track dependencies.
Steps:
- "Get all work items in the 'E-commerce Platform' project"
- "Filter by work item type 'Story' to see feature requirements"
- "Create a new task 'API endpoint for user profiles' in the 'Backend Services' component"
- "Create a dependent task 'Integrate user profile API' in the 'Frontend' component"
- "Check work items assigned to backend team members to see their current workload"
Benefits: Coordinate cross-functional work and ensure proper dependency tracking.
Configuration
The server requires configuration for authentication and connection to your Plan instance. You can provide configuration in several ways:
Quick Setup (Recommended)
Run the interactive setup script:
npm run setup
This will prompt you for your configuration values and create a .env file automatically.
Option 1: Environment Variables
Set the following environment variables:
export PLAN_ACCESS_TOKEN="your_base64_encoded_token_here"
export PLAN_SERVER_URL="https://your-plan-server.com/plan"
export PLAN_TEAMSPACE_ID="your-teamspace-id-here"
Option 2: Command Line Arguments
Pass configuration as command line arguments:
node src/lib/server.js --token "your_token" --server-url "https://your-server.com/plan" --teamspace-id "your-teamspace-id"
Option 3: Environment File
Copy .env.example to .env and fill in your values:
cp .env.example .env
# Edit .env with your actual configuration values
Installation
Option 1: Direct NPX Usage (Recommended)
You can run the MCP server directly without installation:
npx @securedevops/mcp-devops-plan --token "your_token" --server-url "https://your-server.com/plan" --teamspace-id "your-teamspace-id"
Option 2: Global Installation
npm install -g @securedevops/mcp-devops-plan
mcp-devops-plan --token "your_token" --server-url "https://your-server.com/plan" --teamspace-id "your-teamspace-id"
Option 3: Local Development
git clone https://github.com/securedevops/mcp-devops-plan.git
cd mcp-devops-plan
npm install
npm run setup # Interactive configuration setup
npm start # Start the MCP server
Use with Claude Desktop
Option 1: NPX (Recommended)
Add the following to your Claude Desktop MCP configuration:
{
"mcpServers": {
"devops-plan": {
"command": "npx",
"args": [
"@securedevops/mcp-devops-plan",
"--token", "your_token_here",
"--server-url", "https://your-server.com/plan",
"--teamspace-id", "your_teamspace_id"
]
}
}
}
Option 2: Environment Variables with NPX
{
"mcpServers": {
"devops-plan": {
"command": "npx",
"args": ["@securedevops/mcp-devops-plan"],
"env": {
"PLAN_ACCESS_TOKEN": "your_token_here",
"PLAN_SERVER_URL": "https://your-server.com/plan",
"PLAN_TEAMSPACE_ID": "your_teamspace_id"
}
}
}
}
Option 3: Local Installation
Add the following to your Claude Desktop MCP configuration:
{
"mcpServers": {
"devops-plan": {
"command": "node",
"args": ["/path/to/mcp-devops-plan/src/lib/server.js"],
"env": {
"PLAN_ACCESS_TOKEN": "your_token_here",
"PLAN_SERVER_URL": "https://your-server.com/plan",
"PLAN_TEAMSPACE_ID": "your_teamspace_id"
}
}
}
}
Or with command line arguments:
{
"mcpServers": {
"devops-plan": {
"command": "node",
"args": [
"/path/to/mcp-devops-plan/src/lib/server.js",
"--token", "your_token_here",
"--server-url", "https://your-server.com/plan",
"--teamspace-id", "your_teamspace_id"
]
}
}
}
Usage
The MCP DevOps Plan server provides the following tools for interacting with DevOps Plan:
Available Tools
1. get_applications
Purpose: Retrieves all applications from the Plan system Parameters: None Usage: Use this to get a list of all available applications in your Plan instance. This is typically the first step to understand what applications you can work with.
2. get_available_projects
Purpose: Get the list of projects in Plan for a given application Parameters:
application(string): Name of the plan application Usage: Once you have an application name, use this to see all projects within that application.
3. get_available_components
Purpose: Get the list of components for a project in Plan for a given application Parameters:
application(string): Name of the applicationprojectId(string): ID of the project Usage: Retrieve available components within a specific project. Components are optional organizational units for work items.
4. get_available_workitem_types
Purpose: Get the available work item types for a project in Plan for a given application Parameters:
application(string): Name of the applicationprojectId(string): ID of the project Usage: Get the list of work item types (e.g., Task, Bug, Story) available in a specific project. This is needed before creating work items.
5. create_work_item
Purpose: Creates a new work item in Plan Parameters:
component(string, optional): An optional component name if any are available in the projecttitle(string): Title of the work itemdescription(string): Description of the work itemworkItemType(string): Type of the work item from the list of available work item typesapplication(string): Name of the applicationprojectId(string): ID of the project Usage: Create new work items like tasks, bugs, or stories in a specific project.
6. get_work_items
Purpose: Retrieves all work items for a given application, can filter by work item type and specific owner Parameters:
applicationName(string): Name of the applicationprojectId(string): ID of the projectworkitemType(string, optional): Type of the work item to filter by, if anyowner(string, optional): Filter the work items by owner, if any Usage: List existing work items with optional filtering. Use this to see current work items, track progress, or find specific items.
7. delete_work_item
Purpose: Deletes a work item in Plan Parameters:
dbid(string): The dbid field from the work item to identify it (this is the first field returned for each work item in the get_work_items tool)application(string): Name of the application Usage: Remove work items that are no longer needed. The dbid can be obtained from the get_work_items tool output.
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。