MCP Atlassian Server (by phuc-nt)

What's New in Version 2.1.1 🚀

• Refactored the entire codebase to standardize resource/tool structure, completely removed the content-metadata resource, and merged metadata into the page resource.
• New developer guide: anyone can now easily extend and maintain the codebase.
• Ensured compatibility with the latest MCP SDK, improved security, scalability, and maintainability.
• Updated docs/introduction/resources-and-tools.md to remove all references to content-metadata.

👉 See the full CHANGELOG for details.

What's New in Version 2.0.1 🎉

MCP Atlassian Server v2.0.1 brings a major expansion of features and capabilities!

• Updated APIs: Now using the latest Atlassian APIs (Jira API v3, Confluence API v2)
• Expanded Features: Grown from 21 to 48 features, including advanced Jira and Confluence capabilities
• Enhanced Board & Sprint Management: Complete Agile/Scrum workflow support
• Advanced Confluence Features: Page version management, attachments handling, and comment management
• Improved Resource Registration: Fixed duplicate resource registration issues for a more stable experience
• Documentation Update: New comprehensive documentation series explaining MCP architecture, resource/tool development

For full details on all changes, improvements, and fixes, see the CHANGELOG.

Introduction

MCP Atlassian Server (by phuc-nt) is a Model Context Protocol (MCP) server that connects AI agents like Cline, Claude Desktop, or Cursor to Atlassian Jira and Confluence, enabling them to query data and perform actions through a standardized interface.

Note: This server is primarily designed and optimized for use with Cline, though it follows the MCP standard and can work with other MCP-compatible clients.

• Key Features:
  • Connect AI agents to Atlassian Jira and Confluence
  • Support both Resources (read-only) and Tools (actions/mutations)
  • Easy integration with Cline through MCP Marketplace
  • Local-first design for personal development environments
  • Optimized integration with Cline AI assistant

The Why Behind This Project

As a developer working daily with Jira and Confluence, I found myself spending significant time navigating these tools. While they're powerful, I longed for a simpler way to interact with them without constantly context-switching during deep work.

The emergence of AI Agents and the Model Context Protocol (MCP) presented the perfect opportunity. I immediately saw the potential to connect Jira and Confluence (with plans for Slack, GitHub, Calendar, and more) to my AI workflows.

This project began as a learning journey into MCP and AI Agents, but I hope it evolves into something truly useful for individuals and organizations who interact with Atlassian tools daily.

System Architecture

graph TD
    AI[Cline AI Assistant] <--> MCP[MCP Atlassian Server]
    MCP <--> JiraAPI[Jira API]
    MCP <--> ConfAPI[Confluence API]
    
    subgraph "MCP Server"
        Resources[Resources - Read Only] 
        Tools[Tools - Actions]
    end
    
    Resources --> JiraRes[Jira Resources<br/>issues, projects, users]
    Resources --> ConfRes[Confluence Resources<br/>spaces, pages]
    Tools --> JiraTools[Jira Tools<br/>create, update, transition]
    Tools --> ConfTools[Confluence Tools<br/>create page, comment]

Installation & Setup

For detailed in

... View full README on GitHub