Amazon Bedrock 知识库新增基于 AgentCore Gateway 的细粒度权限控制
Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools
如果你在用 Bedrock 知识库做多用户 Agent，权限隔离一直是个麻烦事。这套方案用 AgentCore Gateway 加 MCP 工具把鉴权做到平台层，比自己在应用里写过滤靠谱。做企业 RAG 的开发者值得照着搭一遍。
AWS 发布了一套将 Amazon Bedrock Managed Knowledge Base 以 MCP 工具形式暴露给 AI Agent 的方案，核心组件是 Amazon Bedrock AgentCore Gateway。请求拦截器会注入经过验证的用户身份，AgentCore 独立校验该身份，实现每个用户的差异化访问控制。
方案同时使用基于资源的策略限制对知识库的直接访问，即使绕过 Gateway 也无法越权读取。这样 Agent 在调用知识库检索时，不同用户只能拿到各自权限范围内的内容。
对企业来说，这在多租户或跨部门部署 RAG 场景下解决了权限隔离问题，把身份验证从 Agent 应用层下沉到平台层。已有 Bedrock 知识库的团队可以直接按文中架构落地。
Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools
Learn how to expose an Amazon Bedrock Managed Knowledge Base to AI agents as MCP tools through Amazon Bedrock AgentCore Gateway while keeping per-user access control. A request interceptor injects verified identity, Policy in AgentCore validates it independently, and a resource-based policy restricts direct access to the knowledge base.
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Amazon Bedrock, AgentCore, MCP/工具, RAG.
Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.