<?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 Chris Reddington</title><link>https://chrisreddington.com/tags/mcp/</link><description>Recent content in MCP on Chris Reddington</description><generator>Hugo</generator><language>en-gb</language><lastBuildDate>Thu, 16 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://chrisreddington.com/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>An interactive agentic AI mental model</title><link>https://chrisreddington.com/project/agentic-ai/</link><pubDate>Thu, 16 Apr 2026 00:00:00 +0000</pubDate><guid>https://chrisreddington.com/project/agentic-ai/</guid><description>&lt;p&gt;An interactive agentic AI mental model is an interactive guide to how an agentic AI system works. It brings together the moving parts that are easy to talk about separately, but harder to hold as one picture when you are building with agents.&lt;/p&gt;
&lt;p&gt;The project walks through how instructions, capabilities, retrieved context, session state, memory, MCP servers, sandbox execution, tool results, and the Think-Act-Observe loop connect in practice.&lt;/p&gt;
&lt;h2 id="features"&gt;Features&lt;/h2&gt;
&lt;ul&gt;
&lt;li&gt;&lt;strong&gt;Interactive mental model&lt;/strong&gt;: Explore the core components of an agentic AI system in one connected view&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Context engineering focus&lt;/strong&gt;: Understand how context windows, retrieved context, and session state shape agent behaviour&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Operational building blocks&lt;/strong&gt;: See where memory, tool use, MCP servers, and sandbox execution fit into the overall system&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;Practical framing&lt;/strong&gt;: Use the Think-Act-Observe loop as a simple way to reason about how agents work in real workflows&lt;/li&gt;
&lt;/ul&gt;</description></item></channel></rss>