This project provides an MCP (Model Context Protocol) server that integrates with Atlassian tools like Jira and Confluence, enabling AI assistants to interact with these platforms for tasks such as updating Jira issues, searching Confluence, and creating content. It targets developers and power users seeking to leverage AI for workflow automation within their Atlassian ecosystem.

How It Works

The server acts as a bridge, translating natural language commands into specific API calls for Jira and Confluence. It supports various authentication methods, including API tokens, personal access tokens, and OAuth 2.0 for Atlassian Cloud. The integration allows for fine-grained control over which tools are enabled and whether operations are read-only, enhancing security and customization.

Quick Start & Requirements

• Installation: docker pull ghcr.io/sooperset/mcp-atlassian:latest
• Prerequisites: Docker.
• Authentication: API tokens (Cloud), Personal Access Tokens (Server/DC), or OAuth 2.0 (Cloud).
• Configuration: Via environment variables or an .env file.
• IDE Integration: Supports Claude Desktop and Cursor.
• Docs: Quick Start Guide

Highlighted Details

• Supports both Atlassian Cloud and Server/Data Center deployments.
• Offers a wide range of tools for Confluence (search, create/update pages) and Jira (issue management, transitions, comments).
• Includes support for HTTP/HTTPS/SOCKS proxies for secure network configurations.
• Provides an SSE (Server-Sent Events) transport option for server-client communication.

Maintenance & Community

The project is licensed under MIT. Contribution guidelines are available in CONTRIBUTING.md.

Licensing & Compatibility

Licensed under MIT. Compatible with commercial and closed-source applications.

Limitations & Caveats

Some Jira Cloud-specific tools are marked with an asterisk and may not be available on Server/Data Center. Older Confluence versions might require basic authentication. SSL verification can be disabled for self-signed certificates, which should be done with caution.