<?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 Ricky Moorhouse</title>
		<link>https://rickymoorhouse.uk/tags/mcp/</link>
		<description>Recent content in Mcp on Ricky Moorhouse</description>
		<generator>Hugo</generator>
		<language>en-gb</language>
		
		
		
		
			<lastBuildDate>Sun, 21 Jun 2026 00:00:00 +0000</lastBuildDate>
		
			<atom:link href="https://rickymoorhouse.uk/tags/mcp/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>MCP Ponderings</title>
				<link>https://rickymoorhouse.uk/blog/2026/mcp-ponderings/</link>
				<pubDate>Sun, 21 Jun 2026 00:00:00 +0000</pubDate>
				<guid>https://rickymoorhouse.uk/blog/2026/mcp-ponderings/</guid>
				<description>&lt;p&gt;Agents are only as good as the access they have to accurate data and business functions. LLMs have a cut off point as to what they know - they&#39;re trained on a set of data and anything beyond that is unknown to them - therefore to build useful agents you need to provide a way for them to access data beyond that corpus.  This could be more your own business data or just more recent information. To enable this Anthropic &lt;a href=&#34;https://www.anthropic.com/news/model-context-protocol&#34;&gt;introduced Model Context Protocol&lt;/a&gt; (MCP) as an open standard to build these connections to data-sources and tooling.  Since then, MCP has exploded into the most common way of providing tools to AI Agents.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
