GUEST OPINION: As enterprises move AI from experimentation to production, they face a growing connectivity and governance challenge. Organisations no longer route prompts to a single LLM, but orchestrate complex systems where agents communicate with external tools via MCP and collaborate with other agents using emerging agent communication protocols, such as Agent to Agent (A2A). Without unified visibility and control, security gaps emerge, costs spiral, and compliance becomes impossible to verify.
Most solutions address only a fraction of this traffic, leaving enterprises to stitch together multiple point solutions or accept blind spots in their AI infrastructure. Kong Inc., a leading developer of API and AI connectivity technologies, has announced Kong Agent Gateway within the AI Gateway 3.14 release.
According to Kong, this launch positions Kong AI Gateway as the only gateway solution on the market to support advanced LLM, MCP, and agent-to-agent (A2A) use cases. “When enterprises started experimenting with LLMs, the governance challenge, while still difficult, was relatively contained once you had an AI Gateway for LLM traffic. You had a request going to a model, a response coming back, and a gateway in between to enforce policy.
With the right solutions, this becomes manageable pretty quickly,” said Alex Drag, Head of Product Marketing at Kong. “That world is now over. Today’s agentic architectures look nothing like that. Agents are calling tools via MCP. Agents are delegating tasks to other agents via A2A. These other agents are producing and consuming event streams. Data flows in every direction, often with little to no human in the loop, and often with no visibility into what’s actually happening.” “This is the problem we built Kong Agent Gateway to solve.
And now Agent Gateway is GA and prod-ready as of AI Gateway 3.14.” Tackling Critical Enterprise Challenges for the ANZ Region Agent Gateway strengthens Kong’s ability to secure the full AI data path, offering unified governance and observability across all AI traffic types, now including A2A communication over the new A2A protocol.
“Every enterprise is wrestling with the same three challenges: not having full visibility into all AI traffic and resource consumption within an agentic workflow, struggling to adopt AI in a way that helps increase margins, and dealing with issues when moving AI and agentic workloads into production,” said Reza Shafii, SVP of Product at Kong. “We built Agent Gateway to solve this directly. Engineering teams can now govern all of their multi-agent traffic in a single place.
This is the kind of control and connectivity that makes agentic AI workable at enterprise scale.” Mark West, Regional Vice President ANZ at Kong, said the Agent Gateway solution was arriving at an ideal time for organisations across the Asia-Pacific region. “AI adoption is really picking up speed across APAC, and that’s driving a big surge in the volume of LLM and MCP traffic that organisations have to handle,” he said. “On top of that, you’ve now got agent-to-agent communication, adding another layer of complexity.
Google only launched the A2A protocol last year, and we’re already seeing meaningful uptake here as enterprises start moving their agentic workloads closer to production. “The issue is, the more these agents start talking to each other without any proper governance in place, the tougher it gets to keep visibility, control costs, or stay on top of compliance. That’s exactly where Agent Gateway comes in; it gives teams the control they need right when they need it.
“The timing feels particularly good for organisations in our region that are serious about scaling AI in a responsible way.” How Agent Gateway Works Agent Gateway extends Kong AI Gateway with purpose-built capabilities for managing, securing, and observing A2A communication, bringing agent-critical functionality to both an organisation’s AI Gateway and larger AMP (agent management platform).
Combined with Kong’s existing support for LLM traffic management, MCP server connectivity, API Management, and Event Management, Agent Gateway creates a comprehensive governance layer across the entire AI data path, the flow of intelligence across models, applications, tools, and data, enabling customers to enforce consistent policies across all AI traffic from a single control point.
With Agent Gateway, organisations can have: Unified observability across all native AI traffic: Kong Konnect acts as a single observability dashboard for all native AI traffic. Production-ready agentic AI: Security, access control, and audit capabilities to confidently move agentic workloads out of pilot and into production. Cost visibility and control: Granular tracking of token consumption and resource usage across agent workflows, enabling accurate cost allocation and margin optimisation.
Reduced compliance risk: Full audit logging of A2A conversations for regulatory requirements and internal governance policies. Faster time to see value: Teams can focus on building agent capabilities rather than piecing together governance infrastructure, proxies, and custom gateway policies. Agent Gateway is now available in Kong AI Gateway, part of the Kong Konnect platform. To learn more about Kong AI Gateway, visit konghq.com/products/kong-ai-gateway. About Kong Inc.
Kong Inc., a leading developer of API and AI connectivity technologies, is building the connectivity layer of AI. Trusted by the Fortune 500® and AI-native startups alike, Kong’s unified API and AI platform enables organisations to secure, manage, accelerate, govern, and monetise the flow of intelligence across APIs and AI traffic — on any model, any cloud. For more information, visit www.konghq.com.