sooperset/mcp-atlassian

Overview

This is an MCP server that provides a unified interface for Atlassian tools like Confluence and Jira. It exposes resources and tools such as list spaces, search issues, and create pages through the Model Context Protocol for use by AI agents.

Best for

Best for
Developers building AI agents that need to interact with Confluence and Jira

Use cases

• Querying Confluence spaces and pages from an AI agent
• Searching and filtering Jira issues programmatically
• Creating Confluence pages and Jira issues via an MCP client

How to use

Tested with

Claude Desktop, Cursor

Example client config

{\n  "mcpServers": {\n    "mcp-atlassian": {\n      "command": "uvx",\n      "args": ["mcp-atlassian"],\n      "env": {\n        "JIRA_URL": "https://your-company.atlassian.net",\n        "JIRA_USERNAME": "your.email@company.com",\n        "JIRA_API_TOKEN": "your_api_token",\n        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",\n        "CONFLUENCE_USERNAME": "your.email@company.com",\n        "CONFLUENCE_API_TOKEN": "your_api_token"\n      }\n    }\n  }\n}

Notes

This is an MCP server that provides a unified interface for Atlassian tools like Confluence and Jira. It exposes resources and tools such as list spaces, search issues, and create pages through the Model Context Protocol for use by AI agents.

5,314 stars on GitHub. Last updated 2026-04-10. Licensed MIT.

Use cases

• Querying Confluence spaces and pages from an AI agent
• Searching and filtering Jira issues programmatically
• Creating Confluence pages and Jira issues via an MCP client

Pros

• Well-starred open source project with active community
• Covers both Confluence and Jira in one server
• Simple Python installation and configuration

Cons

• Limited to two Atlassian products (no Bitbucket or Opsgenie)
• Requires API tokens and proper network access to your instance
• Dependent on MCP client compatibility and ecosystem maturity

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.