Kong AI Gateway 3.14 Adds Agent-to-Agent Communication Support
The update gives Kong a unified governance layer for the full AI data path as agent-to-agent communication becomes standard in enterprise architectures.
Reporting from 1 source: ASCII.jp.
Kong Inc. released AI Gateway 3.14 with a new Agent Gateway feature that manages LLM, MCP, and agent-to-agent (A2A) traffic from a single control plane. The update addresses visibility, cost, and operational challenges as enterprises move AI from proof-of-concept to production and adopt multi-agent architectures. A Gartner report cited in the announcement notes that AI Gateways and Agent Management Platforms will form the foundation for safe AI deployment.
Reza Shafii, Kong's senior vice president of product, said many companies lack visibility into AI traffic and struggle to deploy AI profitably. The Agent Gateway feature is designed to solve those problems by providing a single control point for all AI traffic, including agent-to-agent communication via the A2A protocol.
The release comes as enterprise AI adoption shifts from single-LLM prompts to multi-agent configurations where agents collaborate and connect to external tools through MCP. Without unified governance, security risks and cost increases emerge. Kong's update adds A2A support to its existing LLM and MCP management, creating a single governance layer for the entire AI data path.
Synthesized by Yomimono from the 1 cited source below, including Japanese-language reporting where cited, then editorially reviewed before publishing.