<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Technology on Vubon Notes</title><link>https://vubon.dev/categories/technology/</link><description>Recent content in Technology on Vubon Notes</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 12 Jul 2026 13:30:00 +0700</lastBuildDate><atom:link href="https://vubon.dev/categories/technology/index.xml" rel="self" type="application/rss+xml"/><item><title>A Deep Dive into Model Context Protocol (MCP)</title><link>https://vubon.dev/posts/model-context-protocol/</link><pubDate>Sun, 12 Jul 2026 13:30:00 +0700</pubDate><guid>https://vubon.dev/posts/model-context-protocol/</guid><description>&lt;p>Think about the last time you wanted to give an AI assistant access to your company&amp;rsquo;s data. Maybe you wanted it to query your internal Postgres database, read your Slack messages, or pull context from your Jira tickets.&lt;/p>
&lt;p>Historically, this meant building a custom, one-off integration for every single data source and every single AI model. You&amp;rsquo;d write a specific plugin for ChatGPT, another for Claude, and yet another for your internal tools. It was a fragmented, unscalable mess of custom API wrappers.&lt;/p></description></item></channel></rss>