DigitalOcean Introduces Action Gateway for Managed Agents
DigitalOcean has launched Action Gateway to govern external API calls made by AI agents within Managed Agents environments. The system decouples provider credentials from model context and enforces centralized policy checks for tool execution.
Verified State Diff
Impact & Verification Analysis
Developers and organizations using DigitalOcean Managed Agents to deploy AI coding or automation agents.
It improves security by preventing AI models from accessing raw credentials and provides a unified audit and policy control point for external tool usage, which is critical for enterprise-grade AI deployments.
Full Fact Overview
DigitalOcean has introduced Action Gateway, a centralized governance layer for AI agents operating within Managed Agents. Previously, agents often managed external API interactions and credentials directly within their local runtime environment, creating security risks and fragmented policy enforcement. Action Gateway shifts this responsibility to a dedicated service that resolves caller identity, validates tool definitions, and enforces granular policies (allow, deny, or human-approval 'ask') before dispatching external API calls. It supports Model Context Protocol (MCP) to allow non-native clients to connect to the same governance infrastructure, ensuring that authorization checks remain consistent regardless of the agent's origin.