DevOps MCP Hub

DevOps MCP Hub

An AI-powered MCP server unifying Jira, GitHub, and Confluence integrations, enabling sprint health analysis, smart issue creation, and release notes generation via natural language.

Category
访问服务器

README

🚀 DevOps MCP Hub

AI-Powered Unified DevOps Integration for Jira, GitHub, and Confluence

A comprehensive Model Context Protocol (MCP) server that enables AI assistants to seamlessly interact with your DevOps tools. Built for the CCTECH Hackathon.

Version Node License


✨ Features

🔧 Core Integrations

Platform Features
Jira Issues, Projects, Sprints, Comments, Attachments, Worklogs
GitHub Repos, PRs, Commits, Branches, Actions, Releases
Confluence Spaces, Pages, Search, Comments, Publishing

🤖 AI-Powered Features

  • 🏥 Sprint Health Analyzer - Comprehensive sprint metrics with risk analysis and recommendations
  • 🧠 Smart Issue Creator (NLP) - Create issues from natural language with AI-suggested properties
  • 📊 Team Workload Dashboard - Visualize team capacity and identify bottlenecks
  • ⏱️ Time Tracking - Full worklog support with team summaries
  • 📝 Release Notes Generator - Auto-generate release notes from Jira + GitHub data

💬 MCP Prompts

Pre-built conversational workflows:

  • Sprint Review Analysis
  • Natural Language Issue Creation
  • Team Standup Generation
  • Workload Analysis
  • Release Notes Generation

🚀 Quick Start

Prerequisites

  • Node.js 18+
  • npm or yarn
  • Access to Jira (required) + GitHub/Confluence (optional)

Installation

# Clone the repository
git clone https://github.com/your-org/devops-mcp-hub.git
cd devops-mcp-hub

# Install dependencies
npm install

# Configure environment
cp .env.example .env
# Edit .env with your credentials

# Build
npm run build

Configuration

Edit .env file with your credentials:

# Jira (Required)
JIRA_BASE_URL=https://your-company.atlassian.net
JIRA_EMAIL=your.email@company.com
JIRA_API_TOKEN=your_api_token

# GitHub (Optional)
GITHUB_TOKEN=your_github_token

# Confluence (Optional)
CONFLUENCE_BASE_URL=https://your-company.atlassian.net
CONFLUENCE_EMAIL=your.email@company.com
CONFLUENCE_API_TOKEN=your_api_token

Add to Cursor

Add to your ~/.cursor/mcp.json:

{
  "mcpServers": {
    "devops-hub": {
      "command": "node",
      "args": ["C:/path/to/devops-mcp-hub/dist/index.js"],
      "env": {
        "JIRA_BASE_URL": "https://your-company.atlassian.net",
        "JIRA_EMAIL": "your.email@company.com",
        "JIRA_API_TOKEN": "your_api_token",
        "GITHUB_TOKEN": "your_github_token",
        "CONFLUENCE_BASE_URL": "https://your-company.atlassian.net",
        "CONFLUENCE_EMAIL": "your.email@company.com",
        "CONFLUENCE_API_TOKEN": "your_api_token"
      }
    }
  }
}

🐳 Docker Deployment

Build and Run

# Build Docker image
docker build -t devops-mcp-hub .

# Run with environment file
docker run --env-file .env devops-mcp-hub

# Or with docker-compose
docker-compose up -d

Using Pre-built Image

# Pull from registry (when published)
docker pull your-registry/devops-mcp-hub:latest

# Run
docker run --env-file .env your-registry/devops-mcp-hub:latest

For Teams

Share the Docker image with your team:

# Save image to file
docker save devops-mcp-hub:latest | gzip > devops-mcp-hub.tar.gz

# Load on another machine
gunzip -c devops-mcp-hub.tar.gz | docker load

# Run with their own .env file
docker run --env-file .env devops-mcp-hub:latest

📚 Available Tools

Jira Tools

Tool Description
get_issue Get issue details
search_issues Search with JQL
create_issue Create new issue
update_issue Update issue
delete_issue Delete issue
transition_issue Change status
add_comment Add comment
get_comments Get comments
assign_issue Assign to user
get_projects List projects
get_boards List boards
get_sprints List sprints
get_sprint_issues Sprint issues
get_my_issues My assigned issues
add_worklog Log time
get_worklogs Get worklogs
get_time_tracking Time tracking info

AI Analytics Tools

Tool Description
analyze_sprint_health Sprint health with metrics
get_workload_dashboard Team workload analysis
analyze_issue_text NLP issue analysis
create_smart_issue AI-powered issue creation
generate_release_notes Auto-generate release notes
get_team_worklogs Team time summary

GitHub Tools

Tool Description
github_get_repos List repositories
github_get_repo Repository details
github_get_commits Get commits
github_get_prs Get pull requests
github_compare Compare branches
github_get_file Get file content
github_get_workflows GitHub Actions
github_get_releases Get releases

Confluence Tools

Tool Description
confluence_get_spaces List spaces
confluence_get_page Get page
confluence_search Search content
confluence_create_page Create page
confluence_get_space_pages Pages in space
publish_release_notes_to_confluence Publish release notes

💡 Usage Examples

Sprint Health Analysis

Analyze the health of sprint 123 on board 456

The AI will provide:

  • Health score (0-100)
  • Issue breakdown
  • Risk identification
  • Actionable recommendations

Smart Issue Creation

Create an issue: We need to fix the login page that crashes when users
enter special characters in the password field. This is urgent and
affecting production users.

AI automatically detects:

  • Type: Bug
  • Priority: Critical
  • Labels: frontend, security
  • Similar existing issues

Release Notes Generation

Generate release notes for version 2.0.0 of project MYPROJ

Generates comprehensive release notes with:

  • Features, improvements, bug fixes
  • Breaking changes warnings
  • Contributor acknowledgments
  • GitHub statistics (if configured)

Workload Dashboard

Show me the team workload for project MYPROJ

Provides:

  • Per-member workload metrics
  • Balance score
  • Bottleneck identification
  • Redistribution recommendations

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐
│                     DevOps MCP Hub                          │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐         │
│  │   Jira      │  │   GitHub    │  │ Confluence  │         │
│  │   Client    │  │   Client    │  │   Client    │         │
│  └──────┬──────┘  └──────┬──────┘  └──────┬──────┘         │
│         │                │                │                 │
│         └────────────────┼────────────────┘                 │
│                          │                                  │
│                  ┌───────▼───────┐                          │
│                  │  AI Analytics │                          │
│                  │    Engine     │                          │
│                  └───────┬───────┘                          │
│                          │                                  │
│         ┌────────────────┼────────────────┐                 │
│         │                │                │                 │
│  ┌──────▼──────┐  ┌──────▼──────┐  ┌──────▼──────┐         │
│  │   Sprint    │  │    Smart    │  │   Release   │         │
│  │   Health    │  │    Issue    │  │    Notes    │         │
│  └─────────────┘  └─────────────┘  └─────────────┘         │
│                                                             │
├─────────────────────────────────────────────────────────────┤
│                     MCP Protocol Layer                       │
│              (Tools, Resources, Prompts)                     │
└─────────────────────────────────────────────────────────────┘
                              │
                              ▼
                    ┌─────────────────┐
                    │   AI Assistant  │
                    │  (Cursor, etc)  │
                    └─────────────────┘

🔐 Security

  • No hardcoded secrets - All credentials via environment variables
  • Non-root Docker - Runs as unprivileged user
  • Read-only filesystem - Container filesystem is immutable
  • Input validation - All inputs validated with Zod schemas
  • HTTPS only - All API calls use secure connections

🛠️ Development

# Run in development mode
npm run dev

# Build
npm run build

# Start production
npm start

Project Structure

devops-mcp-hub/
├── src/
│   ├── index.ts           # Main MCP server
│   ├── jira-client.ts     # Jira API client
│   ├── github-client.ts   # GitHub API client
│   ├── confluence-client.ts # Confluence API client
│   └── ai-analytics.ts    # AI-powered analytics
├── dist/                  # Compiled output
├── Dockerfile             # Docker configuration
├── docker-compose.yml     # Docker Compose
├── package.json
├── tsconfig.json
└── README.md

🤝 Contributing

  1. Fork the repository
  2. Create feature branch (git checkout -b feature/amazing-feature)
  3. Commit changes (git commit -m 'Add amazing feature')
  4. Push to branch (git push origin feature/amazing-feature)
  5. Open Pull Request

📄 License

MIT License - see LICENSE file


🏆 CCTECH Hackathon

Built with ❤️ for the CCTECH Hackathon by the DevOps MCP Hub Team

Features Implemented:

  • ✅ Jira MCP Server with full CRUD operations
  • ✅ GitHub Integration
  • ✅ Confluence Integration
  • ✅ AI Sprint Health Analyzer
  • ✅ Smart Issue Creator (NLP)
  • ✅ Team Workload Dashboard
  • ✅ Time Tracking (Worklogs)
  • ✅ Release Notes Generator
  • ✅ Docker Deployment
  • ✅ Cross-platform support (Cloud + Server)

📞 Support

  • Create an issue on GitHub
  • Check existing documentation
  • Review environment configuration

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选