Set it up
-
Turn on Jira in your AI
In Claude: open Settings → Connectors and add Jira. In ChatGPT: Settings → Apps & Connectors.
-
Add it to your app once
Copy the short config below into your app. It just tells your AI where to find Jira.
-
Just ask
Tell it what you want in plain words — no special commands.
For example, say
“List all Jira issues assigned to me that are not in Done status”
Need the exact config? Show it +
Add to your client
{
"mcpServers": {
"jira": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_USERNAME": "your-email@example.com",
"JIRA_API_TOKEN": "<your-jira-api-token>"
}
}
}
}Paste into your client's MCP configuration file.
Ready-to-run prompts
If you ask, Jira does it. Copy one, paste it into Claude, Codex or ChatGPT, done. No setup.
Jira Triage the active sprint
If you ask
“Show me all issues in the current sprint with status 'Blocked' and summarize why each is stuck”
Then
Pull all issues in the active sprint, flag blockers, and suggest re-prioritization.
Jira File a bug ticket
If you ask
“Create a Jira bug in project PAY titled 'Checkout fails on Safari' with the repro steps I just described”
Then
Turn a bug description into a properly-formatted Jira ticket in the right project.
Jira Report across projects
If you ask
“Find all issues labeled 'security' across all projects that aren't closed”
Then
Run JQL-style queries to pull issues across multiple projects for status reports.
In the wild
“I have had some positive experiences using the Jira and Confluence MCPs. However, I use a third-party MCP because my company has a data centre deployment of Jira and Confluence”
“I set up an MCP for jira, to hopefully avoid me from ever opening jira again. i will just talk to the LLm, and ask it to set a task to in progress, tell me what to work on next, add tasks to sprints”
“i connected Claude Code through MCP with Jira (sse). I asked it to create a plan for a specific Jira issue”
Good to know
- · Requires a Jira API token plus your Atlassian account email — the token alone is not enough
- · Cloud and Server/Data Center versions behave differently — some operations are Cloud-only
- · Custom fields have non-obvious internal IDs — you'll often need to look them up the first time
When to use
- ✓ Your team uses Jira as the source of truth for tickets and sprints
- ✓ You need to file bugs or stories from conversation without context-switching
- ✓ You want to run sprint planning queries through conversation
- ✓ You're coordinating cross-project work and need to pull issue lists by filter
When not to use
- × You use Linear, GitHub Issues, or Shortcut (use those specific servers)
- × You need to edit Jira automations, workflows, or custom field schemes
- × You need Confluence integration — use a separate Confluence server
About
Imagine telling your AI: 'Create a Jira ticket for the payment bug and add it to the current sprint' or 'What issues are blocking the release?' — and it runs Jira for you. This server connects your AI to Atlassian Jira so it can create, update, search, and manage issues, sprints, and projects.
The Jira MCP server connects AI assistants to Atlassian Jira. Create and update issues, manage sprints, query issue lists, track project progress, and interact with Jira's full API — through conversation.
Reduces context switching for engineering teams that use Jira for project management while coding.
Workflows That Use Jira MCP
Works With
Also Consider
FAQ
What does Jira MCP do? +
Imagine telling your AI: 'Create a Jira ticket for the payment bug and add it to the current sprint' or 'What issues are blocking the release?' — and it runs Jira for you. This server connects your AI to Atlassian Jira so it can create, update, search, and manage issues, sprints, and projects.
Do I need to know how to code? +
No. Turn it on in your AI's settings and ask in plain English — no terminal, no coding.
When should I use Jira MCP? +
Reach for it when you need to: Your team uses Jira as the source of truth for tickets and sprints; You need to file bugs or stories from conversation without context-switching; You want to run sprint planning queries through conversation; You're coordinating cross-project work and need to pull issue lists by filter.
When should I avoid Jira MCP? +
Skip it when: You use Linear, GitHub Issues, or Shortcut (use those specific servers); You need to edit Jira automations, workflows, or custom field schemes; You need Confluence integration — use a separate Confluence server.
How do I install Jira MCP? +
In Claude Code, run: claude mcp add jira -e JIRA_URL=https://your-domain.atlassian.net -e JIRA_USERNAME=you@example.com -e JIRA_API_TOKEN=<token> -- uvx mcp-atlassian. Copy-paste configs for Claude Desktop, Cursor, and Windsurf are at the top of this page.
