Configuring Amazon Bedrock AgentCore Gateway for secure access to private resources
AWS just made it easier for enterprises to run AI agents on private data. Here's what changed.
Why it matters
Amazon Bedrock's AgentCore Gateway now supports secure VPC-native access to private resources, enabling enterprises to deploy agentic AI workloads without exposing internal APIs to the public internet. This is a infrastructure-layer feature ship that directly impacts how companies operationalize AI agents in regulated or security-sensitive environments.
The key facts
9 to knowAmazon Bedrock AgentCore Gateway ships Resource Gateway for VPC-native private endpoint access
Two implementation modes: managed and self-managed
Three use cases enabled: private API Gateway endpoints, MCP server integration on EKS, private REST API access
Uses Elastic Network Interfaces (ENIs) provisioned directly in customer VPCs
Published April 30, 2026
Amazon Bedrock AgentCore Gateway feature ships with Resource Gateway construct
Provisions ENIs directly inside customer VPCs
Three use case scenarios documented: private API Gateway endpoints, MCP servers on EKS, private REST APIs
Published April 30, 2026 on AWS ML blog
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: In this post, you will configure Amazon Bedrock AgentCore Gateway to access private endpoints using Resource Gateway, a managed construct that provisions Elastic Network Interfaces (ENIs) directly inside your Amazon VPC, one per subnet. You will explore two implementation modes (managed and…