mcp-atlassian
MCP server for Atlassian tools (Confluence, Jira)
The mcp-atlassian MCP server enables AI assistants to interact programmatically with Atlassian Confluence and Jira through the Model Context Protocol. It provides 98 tools for searching, creating, updating, and managing issues, pages, comments, and other resources across both platforms. The server supports Atlassian Cloud as well as Server and Data Center deployments, making it suitable for organizations using either hosting model. Developers can integrate it with Claude Desktop, Cursor, or other MCP-compatible clients to allow natural language interaction with their Atlassian workspace.
Key Features
Use Cases
- 01Search and retrieve Jira issues assigned to specific team members or projects using natural language queries
- 02Create and update bug tickets, feature requests, and tasks directly from AI assistant conversations
- 03Search Confluence documentation and knowledge bases to find onboarding guides, technical specs, or process documents
- 04Transition Jira issues through workflow states (e.g., move tickets to Done or In Progress)
- 05Create and update Confluence pages for documentation or meeting notes via AI commands
- 06Add comments to Jira issues or Confluence pages as part of automated workflows
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
mcp-atlassian — FAQ
What is mcp-atlassian?+
mcp-atlassian is an MCP server that provides AI assistants with 98 tools to interact with Atlassian Confluence and Jira. It supports both Cloud and Server/Data Center deployments.
How do I install the mcp-atlassian MCP server?+
You can install mcp-atlassian using uvx (recommended), pip, Docker, or from source. The quickest method is adding it to your MCP client configuration with the uvx command and your Atlassian credentials as environment variables.
Which AI clients work with mcp-atlassian?+
The server works with Claude Desktop, Cursor, Autohand Code, and any other MCP-compatible client that supports the Model Context Protocol.
Do I need API keys to use mcp-atlassian?+
Yes, you need Atlassian API tokens (for Cloud) or Personal Access Tokens (for Server/Data Center). Create API tokens at https://id.atlassian.com/manage-profile/security/api-tokens, and provide your Atlassian instance URL and username.
Is mcp-atlassian free to use?+
Yes, mcp-atlassian is open source and released under the MIT license. However, you need a valid Atlassian Jira or Confluence account to connect to.
Does mcp-atlassian support on-premise Atlassian installations?+
Yes, it supports Atlassian Server and Data Center deployments (Confluence v6.0+ and Jira v8.14+) using Personal Access Token authentication instead of API tokens.
How do I install mcp-atlassian?+
Open the source repository on GitHub and follow its README. mcp-atlassian is a mcp server — MCP Agents Market links you directly to the official repo.
Is mcp-atlassian free?+
mcp-atlassian is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.