<?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 Tom Ganz</title>
    <link>https://thecout.com/tags/mcp/</link>
    <description>Recent content in Mcp on Tom Ganz</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 04 Apr 2026 22:08:13 +0100</lastBuildDate>
    <atom:link href="https://thecout.com/tags/mcp/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>From HATEOAS to MCP: Guiding AI Agents Through State Machines</title>
      <link>https://thecout.com/blog/mcptooling/</link>
      <pubDate>Sat, 04 Apr 2026 10:00:00 +0100</pubDate>
      <guid>https://thecout.com/blog/mcptooling/</guid>
      <description>If you let an AI agent loose on an API with 15 tools, it will eventually figure out the right sequence. But it will also try things that don&amp;rsquo;t make sense, hit errors, retry, and waste tokens doing it. The question is: can we make the API itself tell the agent what to do next?&#xA;The Problem Consider an order management system. An order goes through states: pending → confirmed → shipped → delivered.</description>
    </item>
  </channel>
</rss>
