ReadingResearchRadarInvestment framework
Sign in / Sign up
← Back to reading
NewsMaterial3 min readDisconfirmAI Editorial

AWS Proposes Centralized Inspection for AgentCore Gateway Access to Private APIs: Placing VPC Lattice Resource Gateways in the Network Account

Under the constraint that an enterprise network team owns all subnets and all cross-VPC traffic must traverse a central firewall, AWS proposes a tested architectural pattern: the network account creates and owns the VPC Lattice resource gateway, places it in a dedicated VPC, and routes it via Transit Gateway to an inspection VPC. This ensures every request and response from AgentCore Gateway to private APIs and MCP servers passes through the firewall. The article also clarifies three key limitations of this pattern: inability to perform payload inspection, partial bypass of the firewall by certain network paths, and the tool's inability to identify end-user identity.

2026-11-19 03:05 GMT+8

Many enterprises face an apparently unsolvable conflict in their network architecture: the network team owns all VPCs and subnets, while application teams can only use shared subnets; simultaneously, all cross-VPC traffic must pass through a central firewall for inspection. When AI agents need to call internal private APIs or MCP servers via AgentCore Gateway, both requirements apply at once—the Gateway needs network entry points to reach backends, but those entry points cannot bypass the firewall.

AgentCore Gateway accesses private targets through VPC Lattice resource gateways, offering two modes: Managed mode, where AgentCore creates the resource gateway in the Gateway account (suitable when the Gateway account can own subnets); and Self-managed mode, where the resource gateway is placed in subnets with direct access to the backend (suitable when centralized inspection between the Gateway and tools is not required). Neither mode satisfies both constraints simultaneously. AWS’s proposed solution is a variant of self-managed mode: the network account creates and owns the resource gateway, places it in a dedicated VPC whose subnets are not shared with any account and contain no backends, but routes point to the Transit Gateway, ensuring every request and response traverses the inspection VPC.

Sign in / Sign up
ReadingResearchRadarInvestment framework

The key mechanism enabling this solution lies in how VPC Lattice delivers connections. When creating a Gateway target, AgentCore associates the shared resource configuration with its own VPC Lattice service network. VPC Lattice then delivers connections from that service network to the network interfaces of the resource gateway. This hop is operated by AWS; from the resource gateway’s Elastic Network Interface (ENI) onward, routing and firewall rules take over subsequent paths. This means the AgentCore account does not need to create a Transit Gateway attachment in its own VPC, nor does it need to own any subnets.

This pattern has three explicit limitations. First, no payload inspection: Traffic between the Gateway and the Application Load Balancer (ALB) is end-to-end TLS encrypted; the firewall sees only flow metadata and TLS Server Name Indication (SNI), not the request content. Payload inspection relies on logs from the Gateway, AWS WAF, and ALB. Second, some paths bypass the firewall: The link from the agent to the interface endpoint, the link from the Gateway to the resource gateway, and token requests made by AgentCore to identity providers do not traverse the central firewall. Third, the tool cannot identify end-user identity: When using client credentials authorization, every call reaching the tool carries the Gateway’s client identity. Tracing a call to a specific caller requires examining inbound JWT claims in the Gateway application logs.

For validation, AWS demonstrated a clever test: In the firewall rules, a rule dropping response-direction traffic (drop tcp $TOOL_NET 443 -> $RGW_NET any) was added before the rule allowing request-direction traffic. If responses indeed traversed the firewall, tool calls would hang until timeout, and the firewall logs would record drop events in the to_client direction. Removing the rule restored calls, proving that the response direction does traverse the firewall.

The testing scope was limited to the us-east-1 Region, AWS Network Firewall, and no source NAT. Source NAT, multi-Region deployment, private identity providers, and OpenAPI limitations are discussed in other documentation within the companion repository. AWS recommends running the full set of fourteen validation checks in a non-production copy before adopting the pattern in production environments.

Sources

  • aws.amazon.comAmazon Web Services↗
Continue researching →