Jira and Linear MCP Integration
Your PM just assigned you a ticket with a two-paragraph description and six acceptance criteria. You open your editor, try to remember what the ticket said, start coding, and realize halfway through that you missed a requirement. Then you switch back to Jira, re-read the ticket, copy the acceptance criteria, paste them into a comment in your code, and start over. This context-switching loop repeats dozens of times per sprint.
Project management MCP servers break this loop. The AI reads the ticket directly, understands the requirements, and can even update the ticket status when the work is done.
What You’ll Walk Away With
Section titled “What You’ll Walk Away With”- Setup for Atlassian Rovo MCP (Jira + Confluence) and Linear MCP
- Prompts for ticket-driven development workflows
- Automation patterns for status updates and ticket creation
- Guidelines for combining project management MCP with version control
Atlassian Rovo MCP (Jira + Confluence)
Section titled “Atlassian Rovo MCP (Jira + Confluence)”The official Atlassian MCP server is a remote server that connects via OAuth 2.1. It provides access to Jira issues, Confluence pages, and Compass components.
{ "mcpServers": { "atlassian": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.atlassian.com/v1/mcp"] } }}{ "mcpServers": { "atlassian": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.atlassian.com/v1/mcp"] } }}[mcp.atlassian]transport = "http"url = "https://mcp.atlassian.com/v1/mcp"Linear MCP
Section titled “Linear MCP”For teams using Linear, the Linear MCP integration provides issue management, cycle tracking, and project updates.
Combining PM MCP with Version Control
Section titled “Combining PM MCP with Version Control”The most powerful workflow combines project management and version control MCP servers. The AI reads the ticket, creates a branch, writes the code, opens a PR referencing the ticket, and updates the ticket status — all in one conversation.
- Read the ticket. The AI fetches requirements and acceptance criteria from Jira or Linear.
- Create the branch. Using Git MCP, the AI creates a feature branch named after the ticket ID.
- Implement the change. The AI writes code grounded in the ticket’s requirements.
- Open a PR. Using GitHub MCP, the AI creates a pull request that references the ticket.
- Update the ticket. The AI moves the ticket to “In Review” and adds a comment with the PR link.
When This Breaks
Section titled “When This Breaks”OAuth flow never completes. The Atlassian Rovo MCP requires a browser redirect to localhost. If you are behind a VPN or corporate proxy that blocks localhost callbacks, the OAuth flow will hang. Try disconnecting from the VPN temporarily or using a direct connection.
“Your site admin must authorize this app” error. The first user on your Atlassian site must have access to both Jira and Confluence for the initial OAuth consent. Ask your Atlassian admin to complete the first authorization.
AI cannot find the ticket. Ensure you are using the correct project key. The AI searches using JQL, so “find open bugs in PLATFORM” requires the project key to be “PLATFORM”, not the project name.
Permission denied on ticket updates. The MCP server respects your Atlassian permissions. If you cannot edit a ticket in the Jira web UI, the AI cannot edit it through MCP either.