<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent Gateway on RLGeeX</title><link>https://www.rlgeex.com/tags/agent-gateway/</link><description>Recent content in Agent Gateway on RLGeeX</description><generator>Hugo</generator><language>en-us</language><copyright>RLGeeX © 2025 - Real-Life Geeks providing expert IT consulting</copyright><lastBuildDate>Tue, 01 Sep 2026 09:00:00 -0400</lastBuildDate><atom:link href="https://www.rlgeex.com/tags/agent-gateway/index.xml" rel="self" type="application/rss+xml"/><item><title>Building a Multi-Tenant MCP Proxy: One Endpoint, Three Backends</title><link>https://www.rlgeex.com/news/building-a-multi-tenant-mcp-proxy-one-endpoint-three-backends/</link><pubDate>Tue, 01 Sep 2026 09:00:00 -0400</pubDate><guid>https://www.rlgeex.com/news/building-a-multi-tenant-mcp-proxy-one-endpoint-three-backends/</guid><description>&lt;p>This post is for platform and infrastructure leads wiring agents into real systems. You have a few MCP servers, more than one tenant who needs them, and you want a single endpoint in front of them. My position is that all of the tenancy belongs in the proxy and none of it belongs in the backends. The rest of this post covers the decisions that follow from that and the ones I would not compromise on.&lt;/p></description></item></channel></rss>