<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Kong on Ivan Versluis — Networknet</title><link>https://networknet.nl/tags/kong/</link><description>Recent content in Kong on Ivan Versluis — Networknet</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 15 Sep 2026 16:05:17 +0200</lastBuildDate><atom:link href="https://networknet.nl/tags/kong/index.xml" rel="self" type="application/rss+xml"/><item><title>Building a Kong gateway foundation for APIs, LLMs and MCP</title><link>https://networknet.nl/notes/kong-api-llm-mcp-gateway/</link><pubDate>Tue, 15 Sep 2026 13:00:00 +0200</pubDate><guid>https://networknet.nl/notes/kong-api-llm-mcp-gateway/</guid><description>&lt;h2 id="from-ingress-controller-to-integration-boundary">From ingress controller to integration boundary&lt;/h2>
&lt;p>Kong has been part of my Kubernetes homelab for some time. Initially, its role was relatively conventional: terminate TLS, provide ingress and apply policies before traffic reached a workload.&lt;/p>
&lt;p>That role has changed.&lt;/p>
&lt;p>As I added LLM integrations, MCP servers and automation around n8n and OpenClaw, I started seeing the same problem from different directions. Each new integration could easily introduce another direct connection, another credential and another piece of application-specific configuration.&lt;/p></description></item></channel></rss>