<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>MCP on Nahuel Hernandez</title>
    <link>https://nahuelhernandez.com/tags/mcp/</link>
    <description>Recent content in MCP on Nahuel Hernandez</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <lastBuildDate>Thu, 19 Feb 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://nahuelhernandez.com/tags/mcp/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Running MCP Servers on EKS: Architecture for Production Agentic Workloads</title>
      <link>https://nahuelhernandez.com/blog/mcp_servers_on_eks_production/</link>
      <pubDate>Thu, 19 Feb 2026 00:00:00 +0000</pubDate>
      
      <guid>https://nahuelhernandez.com/blog/mcp_servers_on_eks_production/</guid>
      <description>For most of 2025, MCP servers lived on developer laptops. You connected your editor or your local Claude client to a stdio process, the process held a session, you were the only user. Production was not a concern because there was no production.
That changed quickly. By the back half of 2025, internal teams started exposing MCP servers as shared infrastructure. Wrap an internal API, an EKS cluster, a Postgres database, or a SaaS account in MCP, deploy it, point an agent or a fleet of agents at it.</description>
    </item>
    
  </channel>
</rss>
