用 VPC Lattice 让 Amazon Bedrock AgentCore Gateway 接入集中检查网络中的私有 API
Connect Amazon Bedrock AgentCore Gateway to private APIs in a hub-and-spoke network with centralized inspection
企业里的智能体经常卡在调不了内网 API 这一步。AWS 这篇给出了完整可抄的网络架构:VPC Lattice resource gateway 放在网络账户里,流量全部过中央防火墙。做企业级智能体、受合规约束的团队直接照着搭就行。
AWS 发布了一个经过验证的网络架构方案,解决企业中心化网络模式下 Amazon Bedrock AgentCore Gateway 无法访问私有 API 和 MCP 服务器的问题。方案的核心是把 VPC Lattice resource gateway 部署在网络账户中,使 AgentCore Gateway 到私有资源的每一跳流量都经过中央防火墙检查。
许多企业采用中心化网络模型:由一个账户统一管理所有 VPC,所有流量必须经过中央防火墙进行安全检查。这个模式与 AgentCore Gateway 的默认部署方式存在冲突,导致智能体无法调用内网中的 API 和 MCP 服务器。
该方案通过 AWS 多账户架构实现,适合受合规要求约束、需要集中管控流量的企业。开发者在为智能体接入企业内部系统时,可以直接参考这篇带有实测验证的部署模式。
Connect Amazon Bedrock AgentCore Gateway to private APIs in a hub-and-spoke network with centralized inspection
Many enterprises run a centralized network model: one account owns every VPC and a central firewall inspects all traffic. This post shows a tested pattern for connecting Amazon Bedrock AgentCore Gateway to private APIs and MCP servers in that model, with the VPC Lattice resource gateway in the network account so every hop crosses the firewall.
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 Gateway, VPC Lattice, MCP and tools.
Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.