Atlassian MCP
About
An MCP server for Jira and Confluence (the community-favorite implementation) supporting Cloud and Server/Data Center, letting agents search, create and update issues and pages in natural language, with API token, PAT and OAuth 2.0 auth.
Our Verdict
Atlassian MCP brings productivity capabilities to the MCP ecosystem. Its GitHub popularity reflects community trust, and the standardized protocol ensures broad compatibility across AI clients.
Pricing
Use Cases
- Integrating productivity capabilities into AI agent workflows
- Building custom AI-powered tools with Atlassian MCP
- Enhancing AI agent functionality with standardized MCP access
Pros
- Atlassian MCP provides standardized MCP protocol access
- Open source with 5,680 GitHub stars
- Active development and community support
Cons
- Requires MCP-compatible client (Claude, Cursor, etc.)
- Setup complexity varies by client
- Some features may depend on client capabilities
Installation
uvx mcp-atlassianFrequently Asked Questions
Is Atlassian MCP an official product?
It is an open-source implementation maintained by community developer sooperset (5,000+ GitHub stars), not an official Atlassian product — but its completeness and active upkeep make it one of the most widely used MCP options for Jira/Confluence today.
Does it support self-hosted Server / Data Center?
Yes. It connects to Atlassian Cloud as well as self-hosted Jira/Confluence Server and Data Center, with auth via API token, Personal Access Token (PAT) and OAuth 2.0 — suitable for on-prem enterprise deployments.
How do I install and configure it?
Run it with uvx mcp-atlassian (Docker and pip are also supported), passing your Jira/Confluence URL and credentials via environment variables (e.g. JIRA_URL, JIRA_USERNAME, API token). See the project docs for full configuration.