<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>llm on krtffl.dev</title>
    <link>https://krtffl.dev/tags/llm/</link>
    <description>Recent content in llm on krtffl.dev</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>© [krtffl](https://krtffl.dev)</copyright>
    <lastBuildDate>Mon, 30 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://krtffl.dev/tags/llm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>building three mcp servers in rust with rmcp</title>
      <link>https://krtffl.dev/posts/mcp-servers-in-rust/</link>
      <pubDate>Mon, 30 Mar 2026 00:00:00 +0000</pubDate>
      
      <guid>https://krtffl.dev/posts/mcp-servers-in-rust/</guid>
      <description>&lt;p&gt;i wanted to ask an llm &amp;ldquo;is my server on fire?&amp;rdquo; without ssh-ing into the box, running &lt;code&gt;htop&lt;/code&gt;, squinting, giving up, and running &lt;code&gt;docker ps&lt;/code&gt; instead. i wanted it to just &lt;em&gt;know&lt;/em&gt; — pull the cpu number, list the containers, hit prometheus, and tell me in a sentence.&lt;/p&gt;
&lt;p&gt;the model context protocol makes that possible. you hand an llm a set of tools, it decides when to call them. fine. so i built one server for my infra. then i wanted one for spanish government open data — the boe, the tax calendar, the property registry. then a third for formula 1 telemetry, because it&amp;rsquo;s my blog and i do what i want.&lt;/p&gt;
&lt;p&gt;three servers. and i could already see the future: three near-identical binaries, three copies of the same http-client boilerplate, three subtly different cache bugs. the copy-paste tax.&lt;/p&gt;</description>
    </item>
    
  </channel>
</rss>
