Oracle Expands Support for Agentic AI with MCP Integration

Oracle has become the latest data management provider to embrace the growing trend of agentic AI development by adding support for the Model Context Protocol (MCP).

MCP, developed by generative AI vendor Anthropic, is an open standard designed to streamline how AI agents connect with training resources, like databases and large language models (LLMs). This initiative aims to enhance the safety and efficacy of autonomous AI operations.

Major tech companies such as AWS and Google have already adopted MCP, alongside data platforms like Databricks, Snowflake, and various specialists in data management. As of July 16, Oracle Database is now integrated with MCP servers, a move that improves the training processes for agentic AI applications and sets a new standard for interoperability.

"It is the widely adopted standard to tell AI models what can be accessed outside of what is stored, added and learned by them in training, which is super important for training processes such as retrieval-augmented generation," said Holger Mueller, an analyst at Constellation Research.

This integration allows Oracle users to leverage MCP via the command-line interface (CLI) to connect their databases securely with MCP tools. While the setup is straightforward, caution is advised with respect to data exposure concerns.

As Oracle continues to evolve, analysts stress the need for ongoing improvements to keep pace with current trends in data management and analytics. Future developments could enhance accessibility and usability for non-technical business users, ensuring SQL queries can be efficiently executed through AI interfaces.