<?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 t0ul</title><link>https://t0ul.com/tags/mcp/</link><description>Recent content in Mcp on t0ul</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 24 Feb 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://t0ul.com/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>A pinned tool catalog</title><link>https://t0ul.com/blog/a-pinned-tool-catalog/</link><pubDate>Tue, 24 Feb 2026 00:00:00 +0000</pubDate><guid>https://t0ul.com/blog/a-pinned-tool-catalog/</guid><description>&lt;p&gt;&lt;em&gt;Part of my &lt;a href="https://t0ul.com/blog/the-plan/"&gt;AI Security Engineering&lt;/a&gt; series, a local email-to-calendar agent I build, then attack, then harden. If you have not set up the lab yet, start with &lt;a href="https://t0ul.com/blog/setting-up-the-lab/"&gt;Set up your lab&lt;/a&gt;. The lessons are &lt;a href="https://github.com/t0ul/ai-security-engineering"&gt;on GitHub&lt;/a&gt;, and the agent itself lives at &lt;a href="https://github.com/t0ul/emaildrop"&gt;t0ul/emaildrop&lt;/a&gt;.&lt;/em&gt;&lt;/p&gt;
&lt;h2 id="a-plan-can-be-honest-and-still-go-wrong"&gt;A plan can be honest and still go wrong&lt;/h2&gt;
&lt;p&gt;The last post made the hand-off between the agent&amp;rsquo;s brains unforgeable. A plan now provably comes from the real planner, unaltered. But an authentic plan still names tools, and it reaches for them through MCP, the Model Context Protocol, where a server advertises a catalog of tools and the model reads each tool&amp;rsquo;s description to decide how to use it. The plan can be perfectly genuine and still call a tool whose definition is not what it was when you approved it.&lt;/p&gt;</description></item></channel></rss>