MCP Atlassian

What is MCP Atlassian?

MCP Atlassian is a Model Context Protocol (MCP) server that integrates AI assistants with Atlassian Confluence and Jira, supporting both Cloud and Server/Data Center deployments.

How to use MCP Atlassian?

Configure your MCP client (e.g., Claude Desktop, Cursor) with the uvx command and set environment variables for JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_USERNAME, and CONFLUENCE_API_TOKEN (or JIRA_PERSONAL_TOKEN for Server/Data Center). Then ask natural language queries like “Find issues assigned to me” or “Search Confluence for onboarding docs.”

Key features of MCP Atlassian

• 77 tools covering Jira and Confluence operations
• JQL search for issues and CQL search for pages
• Create, read, update, and transition Jira issues
• Create, read, update Confluence pages and add comments
• Supports Cloud and Server/Data Center (Jira ≥8.14, Confluence ≥6.0)

Use cases of MCP Atlassian

• Find issues assigned to a user in a project
• Search Confluence for onboarding documentation
• Create a bug ticket for a reported issue
• Update the status of a Jira issue to Done

FAQ from MCP Atlassian

Can I use MCP Atlassian with Jira Server or Data Center?

Yes, Jira Server/Data Center v8.14+ is supported using a Personal Access Token instead of username and API token.

How many tools does MCP Atlassian provide?

It provides 77 tools total, covering Jira and Confluence operations like search, create, update, and transition.

Is MCP Atlassian an official Atlassian product?

No, it is an MIT-licensed community project and not an official Atlassian product.

What environment variables are required to configure MCP Atlassian?

You need JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_USERNAME, and CONFLUENCE_API_TOKEN (or JIRA_PERSONAL_TOKEN for Server/Data Center).

Can I use MCP Atlassian with Confluence Cloud?

Yes, Confluence Cloud is fully supported.