Strategy Mosaic and Amazon Bedrock AgentCore build semantic layers for agents
Build a semantic layer for agentic AI on AWS with Strategy Mosaic and Amazon Bedrock AgentCore
The non-obvious part is that governance travels through the MCP server: an agent querying a semantic layer still respects per-user row and column security, which removes the usual fear of agents leaking data they can technically reach. Data engineers and agent builders on AWS can follow the walkthrough to combine Redshift, Aurora, Strands and AgentCore into one governed setup. It also serves as a concrete reference implementation of MCP in an enterprise BI context.
AWS published the third post in its semantic-layer blog series on 2026, demonstrating how to build a customer 360 view spanning Amazon Redshift and Amazon Aurora using Strategy Mosaic. The post exposes that semantic layer to a Strands agent running on Amazon Bedrock AgentCore via the Mosaic MCP server. Per-user row and column security is enforced end-to-end across the pipeline.
Build a semantic layer for agentic AI on AWS with Strategy Mosaic and Amazon Bedrock AgentCore
The third post in our semantic-layer series builds a customer 360 across Amazon Redshift and Amazon Aurora with Strategy Mosaic, exposes it to a Strands agent on Amazon Bedrock AgentCore through the Mosaic MCP server, and enforces per-user row and column security end-to-end.