How to build a semantic layer for agentic AI with Denodo and Amazon Bedrock AgentCore
AIAWS Machine Learning Blog describes building a semantic layer for agentic AI using the Denodo Platform and Amazon Bedrock AgentCore. The Denodo MCP Server exposes governed views to a Strands agent, which queries Amazon Aurora, Amazon Redshift, and an on-premises PostgreSQL database through VQL without moving data between sources.
AIWhy it matters.
The post walks through federating Aurora, Redshift, and on-premises PostgreSQL behind an MCP-exposed semantic layer, with identity propagation and row and column policies for an agent.
Source details
AWS Machine Learning Blog · Suntosh Murthy · aws.amazon.comPublished · added here
Original title: Build a semantic layer for agentic AI on AWS with Denodo and Amazon Bedrock AgentCore