用 Denodo 与 Amazon Bedrock AgentCore 在 AWS 上构建智能体语义层
原标题：Build a semantic layer for agentic AI on AWS with Denodo and Amazon Bedrock AgentCore
AI 摘要
AWS 博客介绍如何用 Denodo 平台作为语义层，配合 Amazon Bedrock AgentCore 构建 agentic AI 应用。方案将 Amazon Aurora、Amazon Redshift 与本地 PostgreSQL 联邦为统一的客户 360 视图，通过 Denodo MCP Server 以 MCP 协议向 AgentCore 托管的智能体暴露受治理视图，并利用 AgentCore Identity 的 On-Behalf-Of 令牌交换传递用户身份，由 Denodo 全局安全策略在查询时执行行列过滤。
正文节选
Build a semantic layer for agentic AI on AWS with Denodo and Amazon Bedrock AgentCore Agentic AI applications need governed access to live enterprise data. That data can live in operational systems, analytical warehouses, SaaS applications, other clouds, or on premises. In the previous post in this series, we built a semantic layer on AWS using Stardog’s knowledge graph over Amazon Aurora and Amazon Redshift. A Strands agent on Amazon Bedrock AgentCore queried that layer. Amazon Bedrock AgentCor