{
  "id": 17093744,
  "title": "How MoEngage turned over 400 APIs into agent tools with AgentCore Gateway",
  "url": "https://urgent.news/2026/10/29/how-moengage-turned-over-400-apis-into-agent-tools-with-agentcore",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-29T16:54:52.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/how-moengage-turned-over-400-apis-into-agent-tools-with-agentcore-gateway/"
  },
  "original_language": "en",
  "account": "MoEngage, a leading agentic customer engagement platform used by over 1,350 consumer brands, faced the challenge of making hundreds of private APIs accessible to AI agents securely and efficiently. The platform relied on roughly 400 internal REST APIs running in private VPCs across seven AWS Regions, with no public exposure. To address this issue, MoEngage implemented AgentCore Gateway, a feature of Amazon Bedrock AgentCore, to convert these private APIs into permission-scoped agent tools. This solution saved an estimated six months of engineering effort and streamlined the onboarding process for new APIs, making it much easier and faster.",
  "summary": "MoEngage turned roughly 400 private REST APIs across 7 AWS Regions into permission-scoped agent tools with Amazon Bedrock AgentCore Gateway. No per-service MCP servers, no public endpoints, and no 400-tool context bloat. See how OpenAPI specs, Cedar policies, and managed Amazon VPC Lattice egress made it work.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}