MoEngage uses Amazon Bedrock AgentCore Gateway to expose 400 internal APIs as agent tools
MoEngage, a customer‑engagement platform used by more than 1,350 consumer brands, operates roughly 400 internal REST APIs built by 25 engineering teams across seven AWS regions. The company needed AI agents to call these APIs safely, without public exposure, without giving models direct control over identity, and without flooding context windows with hundreds of tool definitions.
Key points
- MoEngage turned ~400 private APIs into agent tools via Amazon Bedrock AgentCore Gateway.
- The managed solution eliminated 20+ MCP servers, cutting platform engineering effort by an estimated six months.
- Onboarding a new API now takes hours, not days, with no public endpoints and server‑side policy scoping.
To solve this, MoEngage adopted Amazon Bedrock AgentCore Gateway, a fully managed Model Context Protocol (MCP) server. By registering OpenAPI specs, the gateway automatically generates MCP tools, applies Cedar policies for per‑agent authorization, and routes calls through managed egress over Amazon VPC Lattice. This eliminated the need for more than 20 separate MCP servers, saved an estimated six months of platform‑engineering effort, and cut the onboarding time for a new API from days to hours.
The deployment now runs in seven regions, serving about 400 registered API operations to ten internal agents. It uses SigV4 signing for identity, keeps all traffic private via VPC interface endpoints, and offers semantic search so agents receive only the tools they need, keeping context windows small and execution efficient.
The story so far
4 episodes →- MoEngage uses Amazon Bedrock AgentCore Gateway to expose 400 internal APIs as agent toolsthis story
How MoEngage turned over 400 APIs into agent tools with AgentCore Gateway
AWS Machine Learning Blog · 29 October 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Nikhil Kumar. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Claude Code finds all 5 planted vulnerabilities in 8 minutes · 1 src
- Zapier adds Gemini 3.8 Flash to workflows via AI by Zapier · 1 src
- How to Create a Realistic Cyberpunk-Style Apartment Complex with Claude Opus 5.5 and Blender MCP · 1 src
- Forever Security warns of malicious agents.md files triggering Codex and Claude Code · 1 src
- Thoughtworks warns developers hesitate to fully trust coding agents in production · 1 src
Comments
via GitHub Discussions