Connect AI to Jira and Confluence
MCP server connecting AI agents to Atlassian Jira and Confluence for issue management, sprint operations, and wiki tasks through standardized tools.
Why it matters
Empower AI agents to interact with Atlassian Jira and Confluence. Query project data, manage issues, and control sprints through a standardized interface.
Outcomes
What it gets done
Create, update, and transition Jira issues.
Manage Jira sprints and backlogs.
Query and manage Jira filters and dashboards.
Manage Confluence spaces, pages, and comments.
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/vb-atlassian-server-by-phuc-nt | bash Capabilities
Tools your agent gets
Create new Jira issues
Update existing Jira issues
Transition Jira issues through workflow states
Assign Jira issues to users
Add issues to project backlog
Add issues to specific sprints
Change issue ranking/priority
Create new sprints in Jira
Overview
Atlassian Server (by phuc-nt) MCP Server
What it does
The Atlassian Server MCP connector bridges AI agents (Cline, Claude Desktop, Cursor) with Atlassian Jira and Confluence through the Model Context Protocol. It exposes tools for Jira issue management-create, update, transition, assign-plus sprint and backlog operations, custom filters, dashboards, and Confluence space/page operations with version control and attachments.
How it connects
Use this connector when you need AI agents to interact with Jira workflows: managing issues, working with sprints and backlogs, updating statuses, or handling Confluence pages. It supports teams running Agile processes where an AI assistant can handle board management, filter creation, or working across issues and wiki pages. **When NOT to use:** If you only need read-only Jira reporting without mutations, a simpler REST client suffices. This connector requires API tokens with write permissions; avoid it if your security policy prohibits delegating issue-creation authority to AI agents.
Source README
An MCP server that connects AI agents (Cline, Claude Desktop, Cursor) to Atlassian Jira and Confluence, enabling them to query data and perform actions through a standardized interface.
Installation
Smithery
npx -y @smithery/cli install @phuc-nt/mcp-atlassian-server --client claude
Available Tools
| Tool | Description |
|---|---|
createIssue |
Create new Jira issues |
updateIssue |
Update existing Jira issues |
transitionIssue |
Transition Jira issues through workflow states |
assignIssue |
Assign Jira issues to users |
addIssueToBacklog |
Add issues to project backlog |
addIssueToSprint |
Add issues to specific sprints |
rankIssue |
Change issue ranking/priority |
createSprint |
Create new sprints in Jira |
startSprint |
Start sprint execution |
closeSprint |
Close completed sprints |
createFilter |
Create custom Jira filters |
updateFilter |
Modify existing Jira filters |
deleteFilter |
Delete Jira filters |
createDashboard |
Create new Jira dashboards |
updateDashboard |
Modify existing dashboards |
Features
- Connect AI agents to Atlassian Jira and Confluence
- Support for both resources (read-only) and tools (actions/mutations)
- Complete Jira issue management (view, search, create, update, transition, assign)
- Advanced board and sprint management with Agile/Scrum workflow support
- Project management with detailed project and role information
- Filter and dashboard management with widget support
- Comprehensive Confluence space and page management
- Page version management and attachment handling
- Comment management for Confluence pages
- User management and project role assignment
Usage Examples
Find all my assigned issues
Create new issue about login bug
Notes
Originally developed and optimized for use with Cline, though it follows the MCP standard and works with other MCP-compatible clients. Uses the latest Atlassian APIs (Jira API v3, Confluence API v2). Requires an API token with appropriate permissions. See llms-install.md for detailed setup instructions optimized for AI assistants.
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.