Systems | Development | Analytics | API | Testing

We’re excited to announce the general availability of Kong Insomnia 12!

Traditional API Gateways: Excellent for routing, auth, and microservice traffic; poor at AI workloads. Limitations: Can't track tokens, manage streaming responses, enforce content-level security, or use semantic caching. AI Gateways Purpose-built for LLMs with: Architecture Recommendation: Layered approach: Benefits: Lower costs (20--40%), better performance, centralized governance, future-proof AI infrastructure. Market Context.

Everyone's telling you to innovate faster with AI. Move quicker. Ship more features. Deploy more agents. But before we sprint headlong into the AI revolution, we need to have a proper dollars-and-cents conversation that most companies are avoiding. Disclaimer: Statistics cited in this post were reported in the 2025 State of AI Cost Governance Report by Mavvrik. The data is stark: 84% of companies report more than a 6% hit to gross margin from AI costs.

In January 2025, the OAuth 2.0 Security Best Current Practice became RFC 9700 (RFC 9700 - Best Current Practice for OAuth 2.0 Security). This technical milestone symbolizes a broader transformation. APIs are no longer just developer tools---they're regulated infrastructure powering everything from AI agents to telecom networks. The numbers tell a compelling story.

That’s a wrap on API Summit 2025! At our eighth annual event, the brightest minds in the worlds of APIs and AI gathered in New York City to define the next chapter of digital innovation. We're entering an era where APIs are not just connecting services but connecting intelligence. APIs are the neural pathways of this new AI world, where agents will reason, act, and collaborate through endpoints. At this year's API Summit, we saw how quickly this vision is becoming reality.

One of Kong Gateway’s superpowers is deck, our first-party declarative configuration tool. Tens of thousands of developers all around the world have embraced a text-driven, version-controlled configuration workflow for the world’s most used API Gateway. The deck CLI is an incredible tool, but it only works for Kong Gateway.

Today, we're open-sourcing Volcano SDK, a TypeScript SDK for building AI agents that combines LLM reasoning with real-world actions through MCP tools. Why Volcano SDK? One reason: because 9 lines of code are faster to write and easier to manage than 100+. Without Volcano SDK? You'd need 100+ lines handling tool schemas, context management, provider switching, error handling, and HTTP clients. With Volcano SDK: 9 lines. Look how we compress 100+ lines with the following example: That's it.

If you’ve been following Kong, you know that Kong was the first in the API platform space to introduce an enterprise-grade AI Gateway for LLM workloads. Today, we’ve also introduced a new enterprise-grade MCP Gateway to ensure that you can roll out production-ready MCP deployments. But we are focused on more than just the Gateway. Today, we’re excited to announce additional MCP workflow support in the Konnect Developer Portal and a brand new MCP integration solution, the MCP Composer.

This is the eighth post in a series about reasons to attend API Summit 2025. Check out the previous post here. The first time you push an API to production, you’re excited it’s finally live. You’re relieved that you can move on to your next big project. You’re also nervous. You’ve tested as much as you thought you should, but somewhere in the back of your mind is a whisper of, “What if I missed something? What if the commits are messy?

Disclaimer: All of the opinions stated in this blog are my own and do not represent official Gartner opinions on the API Management and Integration markets or the Magic Quadrant report itself.