MCP is a new way to integrate LLMs and AI agents with third-party data sources and APIs. It significantly improves how we build tool integrations by eliminating duplicated code and providing a centralized interface for multiple agents to access shared tools.
Today, we’re excited to announce the release of Kong’s MCP Server for the Kong Konnect platform. This empowers customers to integrate AI agents and query LLMs to discover APIs, services, and traffic analytics in real time. And — in addition — retrieve complex configuration from federated control planes that have been deployed across the organization.
With this MCP integration, you can enable anybody in your organization — assuming they have the credentials — to quickly understand your API portfolio across every team, view real-time API usage, and check in on policy configurations, ultimately allowing the creation of new business intelligence solutions via AI agents or chat interfaces.
With this new MCP integration — as demonstrated in the video above — you can:
As MCP is being adopted by the most popular LLM providers like Anthropic and OpenAI, it's quickly becoming the de-facto standard for how we connect third parties with our LLMs.
By bringing all API, AI, and eventing connectivity under management of the Kong Konnect platform, you can access this entire system of record of connectivity via MCP to more rapidly build solutions that can increase automation and integration via AI agents.
You can get started with Konnect’s MCP server at the official Git repository, or learn more about Konnect here.
We've talked about why 2026 is the year of AI unit economics . There, we explored the "2025 hangover" where organizations realized that without financial governance, AI isn't just a science project but has become a margin-bleeding cost center. But
If you've used KAi before, you'll notice the difference immediately. The enhanced version has deeper access to your Konnect environment and new tools for debugging, analytics, and configuration management: Active tracing and debugging: KAi can now
Every January, the same resolutions show up: eat better, exercise more, finally learn that language, finally figure out that production use case for AI agents (OK, this one isn’t so typical unless you operate in our universe). But if you're respons
The AI boom has a dirty secret: for most enterprises, it's bleeding money. Every LLM call, every agent invocation, every API request that powers your AI products — they all cost something. And right now, most organizations have no idea what they're
Architecture Overview A multicloud DCGW architecture typically contains three main layers. 1\. Konnect Control Plane The SaaS control plane manages configuration, plugins, and policies. All gateways connect securely to this layer. 2\. Dedicated C
The goal of Integration Platform as a Service (iPaaS) is to simplify how companies connect their applications and data. The promise for the first wave of iPaaS platforms like Mulesoft and Boomi was straightforward: a central platform where APIs, sys
Picture this: you’ve spent months building a slick API that developers love, and it’s already humming behind the scenes in production. But every time someone calls your endpoint, what happens? You get an invisible hit across multiple cost centers, i