<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Architecture on Andrea Cervesato</title><link>https://cervesato.it/tags/architecture/</link><description>Recent content in Architecture on Andrea Cervesato</description><generator>Hugo</generator><language>en</language><copyright>Andrea Cervesato</copyright><lastBuildDate>Sat, 21 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://cervesato.it/tags/architecture/index.xml" rel="self" type="application/rss+xml"/><item><title>Maslow's Hammer and the MCP Debate</title><link>https://cervesato.it/posts/mcp-not-everything-is-a-nail/</link><pubDate>Sat, 21 Mar 2026 00:00:00 +0000</pubDate><guid>https://cervesato.it/posts/mcp-not-everything-is-a-nail/</guid><description>&lt;p&gt;A few days ago, a Principal Software Engineer at Red Hat posted a one-liner on LinkedIn that split the comments section in half:&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;&lt;em&gt;&amp;ldquo;MCP is a layer of unnecessary indirection. A properly documented REST API is enough and works for everyone, not just agents.&amp;rdquo;&lt;/em&gt;&lt;/p&gt;
&lt;/blockquote&gt;
&lt;p&gt;33 reactions, 13 comments, and a thread that surfaced some genuinely good arguments on both sides. I jumped in with &lt;a href="https://www.linkedin.com/posts/rigeldiscala_mcp-is-a-layer-of-unnecessary-indirection-share-7438853936566059008-86oB"&gt;my take&lt;/a&gt;, but a LinkedIn comment is not the right format for a nuanced opinion. So here&amp;rsquo;s the long version.&lt;/p&gt;</description></item></channel></rss>