atlassian/atlassian-mcp-server

Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.

What it solves

This project provides a secure, cloud-hosted bridge that allows AI tools and agents to interact with Atlassian Cloud data in real time. It eliminates the need for users to manually copy-paste information or switch between their AI assistant and various Atlassian products like Jira and Confluence.

How it works

It implements the Model Context Protocol (MCP), acting as a remote server that exposes Atlassian platform data as tools that an AI client can call. It uses OAuth 2.1 or API tokens for authentication, ensuring that the AI's actions are restricted to the user's existing access controls. To optimize context window usage, the server exposes a small set of primary tools and allows the AI client to discover additional tools on demand.

Who it’s for

It is designed for developers, content creators, and project teams who use AI-powered IDEs (like Cursor or VS Code) or AI chat interfaces (like Claude or ChatGPT) and want to integrate their Atlassian workspace data into their workflows.

Highlights

  • Broad Product Support: Integrates with Jira, Confluence, Jira Service Management, Bitbucket, Compass, Loom, and the Teamwork Graph.
  • Multi-Client Compatibility: Works with major AI clients including Claude, ChatGPT, Cursor, VS Code (GitHub Copilot), and Windsurf.
  • **Secure Access: Respects user permissions via OAuth 2.1 and API token authentication.
  • Dynamic Tool Discovery: Prevents context bloat by exposing primary tools first and allowing on-demand discovery of others.

Related

  • Project
    sooperset/mcp-atlassian

    An MCP server that enables AI assistants to search, create, and update content in Jira and Confluence across Cloud and Server/Data Center deployments.

  • Project
    MicrosoftDocs/mcp

    A Model Context Protocol (MCP) server that gives AI assistants direct, real-time access to official Microsoft technical documentation and code samples to prevent hallucinations.

  • Project
    awslabs/mcp

    A collection of Model Context Protocol (MCP) servers that enable AI agents and coding assistants to securely access AWS documentation and manage cloud infrastructure.

  • Project
    github/github-mcp-server

    A Model Context Protocol (MCP) server that enables AI agents to interact with GitHub repositories, issues, pull requests, and CI/CD workflows.

  • Project
    IBM/mcp

    A collection of Model Context Protocol (MCP) servers and tools that enable AI agents to securely interact with IBM products, enterprise data, and cloud infrastructure.