/ connectors · Jira

Connect Jira to Mari

Half your team's decisions live in Jira comments. Why the migration was rolled back, which customer hit the edge case, what the workaround actually was: it's all in tickets nobody reopens. When the same problem comes back a year later, the answer exists and might as well not.

Mari's Jira connector turns ticket history into knowledge your team can query.

What syncs

• Issues from your Jira Cloud site: summary, description, comments, and labels, each issue becoming a searchable document.
• You choose the scope with JQL. Sync one project, several, or a filtered slice (project = OPS AND updated >= -90d). The filter is yours to edit, not a fixed import.
• Incremental sync through Mari's one pipeline: chunk, content-hash, embed. Unchanged issues are never re-embedded.

Connecting takes a minute

Pick Jira from the connector list and fill in your site URL (yourco.atlassian.net), account email, an Atlassian API token, and optionally a JQL filter. Test connection surfaces Atlassian's real error, verbatim. Connect, and a scheduled sync flow keeps it current from then on.

What you get back

Ask "have we hit this before?" and the answer streams with numbered citations back to the exact issues. Jira tickets rank alongside Slack threads, repo commits, and wiki pages in one hybrid search. The workaround from last year's ticket and the commit that shipped it come back in the same answer.

Runs on your infrastructure

Mari is self-hosted and Apache 2.0. Postgres with pgvector is the whole data plane, models run locally through ollama, and every LLM feature has a deterministic fallback. Your tickets never leave your deployment.

Start here

• Quick start: docker compose up to a working knowledge base.
• The docs cover connecting a source step by step.
• Book a demo to see it live.

Also connects: Slack, Confluence, Notion, GitHub, Linear, Zendesk, and more. 12 connectors, one pipeline.