What changed

AWS announced the release of AgentCore Gateway, a fully managed Model Context Protocol (MCP) server that transforms private APIs into secure agent tools. This capability is part of Amazon Bedrock AgentCore and allows organizations to securely expose internal APIs to AI agents without public exposure.

What this means in practice

MoEngage, a customer engagement platform, used AgentCore Gateway to securely integrate over 400 internal REST APIs into agent tools. These APIs, running in private AWS VPCs across seven regions, were previously inaccessible to AI agents. With AgentCore Gateway, MoEngage eliminated the need for custom MCP servers, reducing onboarding time for new APIs from days to hours. The solution ensures that identity and authorization are managed server-side, preventing models from accessing sensitive context.

Limitations and availability

AgentCore Gateway operates within AWS infrastructure and requires integration with existing OpenAPI specs. It does not expose any public endpoints, ensuring that internal APIs remain private. The solution is available through Amazon Bedrock AgentCore and is designed for organizations with complex API landscapes that need secure, scalable agent integration. The supplied announcement does not specify pricing or availability dates for the service.

Source facts for AWS Introduces AgentCore Gateway for Secure API Integration: How MoEngage turned over 400 APIs into agent tools with AgentCore Gateway This post was co-written with Nikhil Kumar and Shakir Khan from MoEngage. When engineering teams start building AI agents, the capabilities those agents need usually already exist as internal APIs. Campaign creation, segment queries, delivery stats.
Original AINewsTrend explainer based on the cited source. This graphic summarizes source statements; it is not an independent benchmark.

Sources and further reading

  1. awsml: How MoEngage turned over 400 APIs into agent tools with AgentCore Gateway