Provides tools for managing Confluence spaces, pages, search, comments, and publishing release notes, enabling AI assistants to collaborate on documentation.
Provides tools for interacting with GitHub repositories, pull requests, commits, branches, releases, and file contents, enabling AI assistants to manage code workflows.
Provides tools to list and retrieve GitHub Actions workflows, allowing AI assistants to monitor and inspect CI/CD pipelines.
Provides tools for managing Jira issues, projects, sprints, comments, attachments, worklogs, and AI-powered analytics such as sprint health analysis and smart issue creation from natural language.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@DevOps MCP Hub analyze sprint health for project alpha"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Platform | Features |
Jira | Issues, Projects, Sprints, Comments, Attachments, Worklogs |
GitHub | Repos, PRs, Commits, Branches, Actions, Releases |
Confluence | Spaces, Pages, Search, Comments, Publishing |
🏥 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
Pre-built conversational workflows:
Sprint Review Analysis
Natural Language Issue Creation
Team Standup Generation
Workload Analysis
Release Notes Generation
Related MCP server: MCP Atlassian
Node.js 18+
npm or yarn
Access to Jira (required) + GitHub/Confluence (optional)
# 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 buildEdit .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_tokenAdd 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"
}
}
}
}# 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# Pull from registry (when published)
docker pull your-registry/devops-mcp-hub:latest
# Run
docker run --env-file .env your-registry/devops-mcp-hub:latestShare 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:latestTool | Description |
| Get issue details |
| Search with JQL |
| Create new issue |
| Update issue |
| Delete issue |
| Change status |
| Add comment |
| Get comments |
| Assign to user |
| List projects |
| List boards |
| List sprints |
| Sprint issues |
| My assigned issues |
| Log time |
| Get worklogs |
| Time tracking info |
Tool | Description |
| Sprint health with metrics |
| Team workload analysis |
| NLP issue analysis |
| AI-powered issue creation |
| Auto-generate release notes |
| Team time summary |
Tool | Description |
| List repositories |
| Repository details |
| Get commits |
| Get pull requests |
| Compare branches |
| Get file content |
| GitHub Actions |
| Get releases |
Tool | Description |
| List spaces |
| Get page |
| Search content |
| Create page |
| Pages in space |
| Publish release notes |
Analyze the health of sprint 123 on board 456The AI will provide:
Health score (0-100)
Issue breakdown
Risk identification
Actionable recommendations
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
Generate release notes for version 2.0.0 of project MYPROJGenerates comprehensive release notes with:
Features, improvements, bug fixes
Breaking changes warnings
Contributor acknowledgments
GitHub statistics (if configured)
Show me the team workload for project MYPROJProvides:
Per-member workload metrics
Balance score
Bottleneck identification
Redistribution recommendations
┌─────────────────────────────────────────────────────────────┐
│ 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) │
└─────────────────┘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
# Run in development mode
npm run dev
# Build
npm run build
# Start production
npm startdevops-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.mdFork the repository
Create feature branch (git checkout -b feature/amazing-feature)
Commit changes (git commit -m 'Add amazing feature')
Push to branch (git push origin feature/amazing-feature)
Open Pull Request
MIT License - see LICENSE file
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)
Create an issue on GitHub
Check existing documentation
Review environment configuration
Add a comment to an issue
Inputs: comment (required), issueKey (required).
Log time worked on an issue
Inputs: issueKey (required), timeSpent (required), comment, started.
NLP analysis of issue text for smart suggestions
Inputs: text (required), projectKey (required).
AI-powered sprint health analysis with metrics and recommendations
Inputs: sprintId (required), boardId.
Assign an issue to a user
Inputs: issueKey (required), assignee.
Create a new Jira issue
Inputs: summary (required), projectKey (required), labels, priority, +2 more.
Create issue with AI-suggested type, priority, and labels
Inputs: text (required), projectKey (required), type, priority.
Delete a Jira issue (use with caution!)
Inputs: issueKey (required).
Generate comprehensive release notes
Inputs: version (required), projectKey (required), endDate, startDate, +2 more.
Get attachments on an issue
Inputs: issueKey (required).
Get all Jira boards
Inputs: no named parameters.
Get comments on an issue
Inputs: issueKey (required).
Get details of a specific Jira issue
Inputs: issueKey (required).
Get issues assigned to current user
Inputs: status.
Get project details
Inputs: projectKey (required).
Get all Jira projects
Inputs: no named parameters.
Get issues in a sprint
Inputs: sprintId (required).
Get sprints for a board
Inputs: boardId (required).
Get worklog summary for team
Inputs: endDate, sprintId, startDate, projectKey.
Get time tracking info for an issue
Inputs: issueKey (required).
Get available transitions for an issue
Inputs: issueKey (required).
Team workload analysis with balance metrics
Inputs: sprintId, projectKey.
Get worklogs for an issue
Inputs: issueKey (required).
Save any markdown content directly to a GitHub repository
Inputs: repo (required), owner (required), title (required), content (required), +1 more.
Generate release notes and save to local file or GitHub (no Confluence needed)
Inputs: version (required), projectKey (required), endDate, startDate, +3 more.
Generate and save sprint report to local file or GitHub
Inputs: sprintId (required), boardId, githubRepo, githubOwner, +1 more.
Generate and save workload report to local file or GitHub
Inputs: sprintId, githubRepo, projectKey, githubOwner, +1 more.
Search Jira issues using JQL
Inputs: jql (required), maxResults.
Search for Jira users
Inputs: query (required).
Move an issue to a different status
Inputs: issueKey (required), transitionName (required).
Update an existing Jira issue
Inputs: issueKey (required), labels, summary, priority, +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 31 tools
Most Jira operational tools (get_issue, search_issues, create_issue, etc.) are clearly distinct, but there is overlap in the reporting/generation tools: generate_release_notes vs save_release_notes_to_file vs save_doc_to_github are confusingly similar, as are create_issue and create_smart_issue. An agent could easily select the wrong tool when these overlapping functions are involved.
Every tool name follows a consistent verb_noun pattern (e.g., get_boards, create_issue, analyze_sprint_health, save_doc_to_github). There is no mixing of camelCase or alternate verb styles, making the naming highly predictable.
With 31 tools, the server exceeds the 25-tool threshold for 'too many', making it feel bloated. Many tools are extremely narrow (e.g., get_transitions, get_attachments) and could be consolidated, though the diversity of Jira operations explains some of the count.
The server covers the full Jira issue lifecycle (create, get, update, delete, transition, comment, assign, worklog) plus sprint tracking and AI-based reporting. Minor gaps exist for things like project creation or issue linking, but these are not core to the apparent DevOps hub purpose and can be worked around.
The Jam MCP server provides AI tools with instant bug context without manual prompting, enabling a streamlined workflow from bug identification to ticket creation and pull request generation without switching between tools.
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
A MCP server built for developers enabling Git based project management with project and personal…
