This MCP server enables LLM agents to interact with Atlassian Jira and Confluence Cloud through comprehensive tools for managing issues, pages, and content.
Jira Capabilities:
Search & List Issues: Use JQL queries to find and list issues with customizable result limits
Issue Management: View full issue details, create new issues with project/type specifications, and update issue summaries/descriptions
Comments: Add comments (supports plain text or Atlassian Document Format) and retrieve existing comments
Workflow: Transition issues between statuses using transition IDs and discover available transitions for specific issues
Attachments: Download files attached to Jira issues
Confluence Capabilities:
Page Management: List pages within spaces, view page content/metadata, create new pages (optionally nested under parent pages), and delete pages
Content Editing: Update page content with automatic version handling and support for Mermaid diagrams via code blocks
Search: Perform advanced searches using CQL with customizable result limits and criteria like labels and titles
Comments: Retrieve all comments on Confluence pages
Special Features:
Supports Atlassian Document Format (ADF) for rich text in Jira descriptions and comments
Automatic version management for Confluence page updates with manual control option
Provides tools for interacting with Atlassian Cloud services, including Jira issue management (search, create, update, comment, transition) and Confluence page management (search, view, create, edit, delete).
Allows searching and listing pages within spaces, viewing page content, creating new pages (including nested pages), editing pages with auto-versioning, and deleting pages using CQL search capabilities.
Enables searching issues with JQL, viewing issue details, creating and updating issues with rich text support, adding comments, and transitioning issues through workflows.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@atlassian-mcp-serverlist Jira issues assigned to me that are overdue"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Atlassian MCP Server
A Model Context Protocol (MCP) server that provides powerful tools for interacting with Atlassian Jira and Confluence Cloud. Built with Python and the mcp SDK.
This server enables LLM agents (like Claude Desktop) to:
Jira: Search for issues using JQL, view issue details, add comments, transition issues, and create/update issues (with rich text support).
Confluence: Search space content, view pages, create new pages (including nested pages), and edit pages (with auto-versioning).
Features
Jira Tools
list_jira_issues: Search and list issues using JQL (Jira Query Language).read_jira_issue: Retrieve full details of a specific issue.jira_create_issue: Create new issues (Support for Projects, Issue Types, and ADF Descriptions).jira_update_issue: Update issue summary and description.jira_add_comment: Add comments to issues.jira_get_comments: Retrieve all comments on an issue.jira_download_attachment: Download an attachment (image/document) by its ID.jira_transition_issue: Move issues through their workflow (e.g., To Do -> Done).
Confluence Tools
list_confluence_pages: List pages within a specific space.view_confluence_page: Retrieve page content and metadata.confluence_create_page: Create new pages, optionally nested under a parent page.edit_confluence_page: Update page content (Automatically handles version increments).Note: Includes guidance for handling Mermaid diagrams via the Mermaid Diagrams plugin.
confluence_delete_page: Delete a Confluence page.confluence_search: Perform advanced searches using CQL (Confluence Query Language).confluence_get_comments: Retrieve all comments on a page.
Related MCP server: Jira
Prerequisites
Python: Version 3.10+ (Tested with 3.14.2)
Atlassian Account: An Atlassian account with an API Token.
Setup
Clone and Install:
git clone https://github.com/tingyiy/atlassian-mcp-server.git cd atlassian-mcp-server pip install -r requirements.txtConfiguration: Create a
.envfile in the project root with your credentials:ATLASSIAN_USERNAME=your_email@example.com ATLASSIAN_API_KEY=your_api_token JIRA_URL=https://your-domain.atlassian.net/rest/api/3 CONFLUENCE_URL=https://your-domain.atlassian.net/wiki CONFLUENCE_SPACE_KEY=your_default_space_keyNote:
Run the Server:
python server.py
Usage
This MCP server can be used with any MCP-compliant client, including IDEs (like Cursor, VS Code) and desktop agents (like Claude Desktop).
Generic Configuration
Most MCP clients require the command to run the server and the environment variables.
Command:
python /abs/path/to/atlassian-mcp-server/server.pyEnvironment: All variables from
.envmust be passed to the process.
Claude Desktop
Add the following to your claude_desktop_config.json:
Cursor
To use with Cursor (via the .cursor/mcp.json or settings):
Note: Ensure the python environment has the required dependencies installed.
Confluence Tips: Mermaid Diagrams
The MCP tools cannot render Mermaid diagrams programmatically because the standard plugin stores source code internally. To reference a diagram, provide the Mermaid source in a code block and ask the user to manually render it in the Confluence UI.
Example Agent Output for a Diagram: "I've added the following code block to the page. Please select it in the editor and convert it to a Mermaid diagram:"
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Fork the repository.
Create your feature branch (
git checkout -b feature/AmazingFeature).Commit your changes (
git commit -m 'Add some AmazingFeature').Push to the branch (
git push origin feature/AmazingFeature).Open a Pull Request.
License
Distributed under the MIT License. See LICENSE for more information.