<?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 Danilo Falcão da Silva</title><link>https://falcao.org/tags/mcp/</link><description>Recent content in Mcp on Danilo Falcão da Silva</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 30 May 2026 00:31:38 -0300</lastBuildDate><atom:link href="https://falcao.org/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>MCP Is Where AI Agents Stop Being Toys</title><link>https://falcao.org/posts/mcp-is-where-ai-agents-stop-being-toys/</link><pubDate>Sat, 30 May 2026 00:31:38 -0300</pubDate><guid>https://falcao.org/posts/mcp-is-where-ai-agents-stop-being-toys/</guid><description>&lt;p>I did not start caring about MCP because of the protocol spec. I read
the spec, it is fine, it is JSON-RPC with some sensible primitives, and
on its own it would not have earned a post. I started caring about MCP
the day it changed what an agent &lt;em>is&lt;/em>. Before tool access, an agent
generates text. You read the text, you decide, you act. After tool
access, the agent acts. It opens the pull request, it queries the
database, it restarts the container, it pages someone. The text was a
suggestion. The tool call is an operation.&lt;/p></description></item></channel></rss>