Our new technical article has been published on the Liferay website. In it, we use concrete examples from customer projects to demonstrate how AI agents can assist with content migration via the Liferay DXP MCP Server.
Content migrations are often among the most time-consuming tasks when implementing or modernizing a content management system. Existing content must be analyzed, mapped to new structures, categorized, and reliably transferred to the target system. Traditionally, this requires custom scripts and a significant amount of manual effort.
The approach described in this article shifts a large portion of this work to AI agents. Among other things, they can create content structures, transfer existing content field-by-field, and assign appropriate categories based on their semantic meaning. While this does not make the migration a fully automated process, it does result in a significantly faster and more scalable workflow with targeted human oversight.
Migrations are just the beginning. Once content is structured in the new Liferay CMS, agents can take on additional tasks—such as adapting content for different target audiences, creating newsletters, supporting translation processes, or reusing content across various channels.
The technical foundation for this is the combination of the object-based architecture of the new Liferay CMS, the headless APIs, and the Model Context Protocol. This transforms Liferay into a platform where AI not only generates content but can also perform specific tasks within content processes.
In the full article, we discuss the practical workflow, the potential business value, and the limitations that currently remain.
Read the article on Liferay: “CMS MCP Server: How AI Agents Migrate Content in Liferay”
