{"id":14765,"date":"2026-10-01T11:22:31","date_gmt":"2026-10-01T09:22:31","guid":{"rendered":"https:\/\/actonic.de\/?p=14765"},"modified":"2026-10-01T11:22:31","modified_gmt":"2026-10-01T09:22:31","slug":"report-builder-8-2","status":"publish","type":"post","link":"https:\/\/actonic.de\/en\/report-builder-8-2\/","title":{"rendered":"Report Builder 8.2 Release Notes: AI Report Building with Rovo and MCP"},"content":{"rendered":"

[vc_row el_class=”rb82-intro”][vc_column][vc_column_text css=””]Report Builder 8.2 for Jira Cloud adds AI report building: you describe the report you need in a chat, and an agent builds it in Report Builder<\/a>. The agent can run in Atlassian Rovo or in your own AI client connected over MCP (Model Context Protocol).<\/p>\n

The AI only assembles the report configuration. Report Builder calculates the figures from live Jira data, the same way as for reports you build by hand.<\/p>\n

The AI features are available only in the Cloud (Forge) version of Report Builder, not in Data Center.[\/vc_column_text][\/vc_column][\/vc_row][vc_row][vc_column][vc_column_text css=””]<\/p>\n

Report Builder Assistant: a Rovo agent for Jira reporting<\/h2>\n

Report Builder 8.2 includes a Rovo agent called Report Builder Assistant. It uses your site’s Rovo, so there is no separate AI subscription or API key to set up.<\/p>\n

To open it, click the new AI Assistant<\/strong> button in Report Builder. Rovo Chat opens in a side panel with the agent already selected. On sites where Rovo is turned off, the button is grayed out and the tooltip says why.<\/p>\n

Describe what you need, for example, “hours logged per project this month” or “open bugs in MOBL by priority as a pie chart”. The agent finds the projects and people you mention, writes and validates the JQL, and picks the dimensions and measures.<\/p>\n

Before the agent creates or changes a report, it shows a short card describing what it’s about to do and waits for your confirmation. When the report is ready, Report Builder shows a notification with an Open<\/strong> button, and the report opens in the same tab next to the chat.<\/p>\n

From there you can keep adjusting it in plain language, for example, by splitting it by assignee or limiting it to the current quarter. The report goes into your report list only when you ask the agent to save it.<\/p>\n

Requests work in English, German, Ukrainian and Russian, the languages we tested before the release.
\n[\/vc_column_text][\/vc_column][\/vc_row][vc_row][vc_column][vc_column_text css=””]<\/p>\n

Report Builder MCP server for Claude, Cursor and Codex<\/h2>\n

If your team already works in Claude, Cursor or Codex, you can connect your client to the new Report Builder MCP server and build reports from a chat or your IDE. Any other client that supports remote MCP servers works too.<\/p>\n

Each user connects their own client on the new Configure AI MCP<\/strong> page in the Report Builder menu. Jira access is granted through Atlassian’s OAuth consent screen, and the page then generates a personal MCP token and a configuration snippet to paste into the client. This is done once per user.<\/p>\n

Reports built over MCP start as drafts with a preview link. When you ask for a change, the agent edits the same draft, so the link stays valid. Drafts that nobody saves are deleted after 24 hours.<\/p>\n

Through the MCP server the agent can:<\/p>\n