Jira · Connector
How do we connect Jira to AI agents on our own infrastructure?
Katonic connects to Jira, reads the issues in the project you name and indexes them in the Knowledge Engine on infrastructure you control. Agents answer from those issues with a model you serve, so the issues and the questions are not sent to a public AI service.
What it reads.
From Jira.
- 01Issues
- 02A single project, where you give its key
Through: Jira REST API: v3 for Cloud, v2 for Server and Data Center
Where the content goes
Into a knowledge store you run.Content is pulled into the Knowledge Engine on infrastructure you own or control, and indexed there. Agents answer from it with a model you serve. The documents, the index and the questions are not sent to a public AI service.
How it signs in
In the set-up dialog you give an API token and the email address it belongs to. The connector also supports OAuth 2.0 for Jira Cloud.
The set-up dialog asks for
- Jira URL
- API token
- Project key (optional)
Permissions
Access is set on the source in Katonic. In addition, Katonic reads the permissions of each item from Jira and re-syncs them, every 24 hours by default. Whether an item's own permissions restrict who can retrieve it, or only add to the access set on the source, is a setting an administrator turns on for the cluster.
Katonic reads project roles and applies them to the issues of that project.
Sync
Incremental, by updated date, and full.
You set how often the source is read again, in minutes, hours, days or weeks.
Does Katonic read Jira project permissions?
Yes. It reads project roles and re-syncs them, every 24 hours by default. Whether they restrict retrieval, or only add to the access set on the source in Katonic, is a setting an administrator turns on for the cluster.
Can we limit it to one project?
Yes. You give the project key.
Where are the issues indexed?
In the Knowledge Engine, on infrastructure you own or control. They are not sent to a public AI service.