Atlassian Launches AI Agents in Jira Open Beta, Expands MCP Ecosystem
The move allows organisations to assign tasks to Atlassian Rovo and third-party agents, collaborate with them in comments, and integrate them into structured workflows.
Atlassian Corporation has announced the open beta of AI agents in Jira, embedding agentic capabilities directly into the workflows where teams plan and track work.
The move allows organisations to assign tasks to Atlassian Rovo and third-party agents, collaborate with them in comments, and integrate them into structured workflows.
The company said the update aims to make agent-driven work visible and accountable rather than fragmented across disconnected tools. Because agents operate within Jira’s existing framework, they adhere to project configurations, permissions, audit trails, and approval processes.
“Work is changing fast: people are now orchestrating across agents, tools, and cross-functional teams. Without clear coordination that can easily turn into chaos,” said Tamar Yehoshua, Chief Product and AI Officer at Atlassian. “We’re focused on helping teams turn that complexity into real productivity. With these new capabilities, we’re bringing agents into the tools and workflows customers already love and trust, and giving them an open, governed way to make those agents part of the team at enterprise scale.”
Alongside the beta, Atlassian announced deeper investments in Model Context Protocol (MCP), positioning itself as an open ecosystem for enterprise AI. Enterprises account for nearly 50% of all Rovo MCP Server usage, with paid editions driving 93% of activity.
New releases include MCP skills within Rovo, enabling integrations with apps such as Amplitude, Box, Canva and Figma, and the general availability of the Rovo MCP Server, allowing AI clients like Claude, Cursor and Google’s Gemini CLI to securely connect with Jira and Confluence.
