Atlassian Connector: Jira and Confluence

Updated November 2, 2026 — Le Chat is now Vibe. As of May 28, 2026, Le Chat is now Vibe (still at chat.mistral.ai): a single agent for work and code, carrying over your conversations, settings, and subscriptions. The legacy Le Chat experience remains accessible in Chat mode; in Work mode, agents are now skills (invoked with @), memories are the knowledge base, and deep search is the Deep Research skill. Plans are now called Mistral Free, Pro, Team, and Enterprise. This lesson uses the name Vibe; some menus described here may have changed names or locations.

The Atlassian Suite in Vibe

Atlassian equips millions of teams with two complementary products: Jira for project management and ticket tracking, Confluence for collaborative documentation. The Atlassian MCP connector brings both together behind a single conversational interface. If you spend your days tracking sprints in Jira while maintaining documentation in Confluence, the benefit is immediate: constant switching between the two apps disappears.

Connecting to Atlassian

This connector uses OAuth 2.0, making setup straightforward:

1. In Vibe, open the Connectors tab and select Atlassian
2. Click Connect—an Atlassian authorization window opens
3. Log in to your Atlassian account and grant access
4. Vibe automatically receives the necessary permissions to interact with your Jira projects and Confluence spaces

No tokens to generate, no secrets to copy-paste, and permissions match exactly what your Atlassian account has. This is also a governance win: if a Jira project is closed to you, it’s closed to Vibe too, without extra configuration or risk of accidental scope creep.

Working with Jira

Querying is the primary use case. You check project status in natural language—“What tickets are in progress in the current sprint for the BACKEND project?” or “Show me all unassigned critical bugs in the MOBILE project.”—and Vibe queries the Jira API, filters, and synthesizes the result instead of dumping a raw list.

Creation follows the same conversational logic. Instead of opening a form and filling out seven fields, describe the ticket you want:

“Create a Jira ticket in the BACKEND project with the title ‘Optimize SQL queries for the dashboard’, priority medium, and add a description detailing the performance issue observed.”

Modification works the same way, and this is often where the time savings are most noticeable, because these are micro-actions repeated twenty times a week: “Move ticket BACKEND-142 to status ‘In Review’ and add a comment stating that unit tests passed.” Finally, for sprint tracking, a question like “Which tickets in sprint 23 aren’t finished yet? Give me a progress summary.” replaces manual status report creation.

Working with Confluence

A Confluence space often accumulates years of documentation, some of which no one knows how to find anymore. Assisted search solves this: “Search Confluence for documentation on our payment API architecture.” Page creation is best for capturing information right after an event, while details are fresh:

“Create a Confluence page in the ‘Engineering’ space with a summary of the sprint 23 retrospective. Include the positives, areas for improvement, and agreed actions.”

Updates complete the picture. Since Confluence is collaborative, outdated documentation quickly becomes dangerous because teams continue to rely on it. An instruction like “Update the ‘Deployment Process’ page in Confluence to add the database migration verification step before production deployment.” lowers the cost of updating enough that it actually gets done.

Three Complete Scenarios

At the end of a sprint, the review becomes a single question: “Summarize all completed tickets in sprint 23 of the BACKEND project. For each ticket, list the title, assignee, and type (feature, bug, chore).” Vibe queries Jira and returns a summary table ready to use in a meeting.

During an incident, speed is critical, and the connector lets you open a ticket without leaving the coordination channel: “Create a Jira ticket of type ‘Incident’ with critical priority in the OPS project. Title: ‘Payment Service Unavailable’. Assign it to the On-Call team.”

The third scenario combines both products to ensure traceability, a task rarely done because it’s tedious: “Take the 5 latest resolved tickets in the API project and create a summary Confluence page in the ‘Changelog’ space with a summary of each fix.” Jira provides the raw material, Confluence receives the synthesis.

Best Practices

Be precise in your requests, since a Jira instance easily contains several thousand tickets. Three elements effectively scope a query:

• The project involved (Jira project key)
• The ticket type (bug, story, task, epic)
• The filters needed (status, priority, assignee, sprint)

Keep in mind that your permissions in Vibe are exactly your Atlassian permissions, which simplifies security discussions with your team. Finally, disable the connector in conversations that involve neither Jira nor Confluence: it exposes many tools, and the model performs more efficiently on a reduced scope.

Key Takeaways

• The Atlassian connector uses OAuth 2.0 for seamless connection to Jira and Confluence
• You can query, create, and modify Jira tickets from Vibe
• Confluence search and page creation are also supported
• Your Atlassian access permissions apply identically in Vibe
• Combine Jira and Confluence for automated documentation workflows