<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>SFCC Field Notes - Oleksandr Katerynchuk</title>
  <subtitle>Notes on Salesforce Commerce Cloud (SFCC) architecture, development, and platform internals.</subtitle>
  <link href="https://www.okater.com/feed.xml" rel="self"/>
  <link href="https://www.okater.com/"/>
  <updated>2025-12-11T00:00:00Z</updated>
  <id>https://www.okater.com/</id>
  <author>
    <name>Oleksandr Katerynchuk</name>
  </author>
  <entry>
    <title>SFCC Vibe Coding with an MCP Server</title>
    <link href="https://www.okater.com/posts/sfcc-vibe-coding-mcp-server/"/>
    <updated>2025-12-11T00:00:00Z</updated>
    <id>https://www.okater.com/posts/sfcc-vibe-coding-mcp-server/</id>
    <content type="html">&lt;p&gt;At this point, it is hard to imagine SFCC development without using AI. It speeds things up significantly. Of course, you need to be careful with it, which is a separate &amp;quot;Vibe Coding&amp;quot; topic.&lt;/p&gt;
&lt;p&gt;The specific challenge with SFCC Vibe Coding is that standard LLMs usually aren&#39;t very good with SFCC context.&lt;/p&gt;
&lt;p&gt;To cover that gap, we can use an MCP Server. This allows the AI to actually understand our environment. 📖 &lt;a href=&quot;https://www.linkedin.com/pulse/taming-ai-beast-custom-toolkit-supercharge-copilot-commerce-theunen-0i7se/&quot;&gt;Thomas Theunen describes this concept perfectly here&lt;/a&gt;.&lt;/p&gt;
&lt;p&gt;I created a video guide on how to configure this and a demo showing Copilot automatically fetching error logs to resolve issues.&lt;/p&gt;
&lt;div class=&quot;video-embed&quot;&gt;&lt;iframe src=&quot;https://www.youtube.com/embed/cSs0u9b_vhk&quot; title=&quot;SFCC Vibe Coding with an MCP Server&quot; frameborder=&quot;0&quot; allow=&quot;accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture&quot; allowfullscreen=&quot;&quot; loading=&quot;lazy&quot;&gt;&lt;/iframe&gt;&lt;/div&gt;
&lt;p&gt;MCP Server: &lt;a href=&quot;https://sfcc-mcp-dev.rhino-inquisitor.com/&quot;&gt;https://sfcc-mcp-dev.rhino-inquisitor.com&lt;/a&gt; (Creator: Thomas Theunen)&lt;/p&gt;
&lt;p&gt;There are some security concerns:&lt;/p&gt;
&lt;ol&gt;
&lt;li&gt;&lt;strong&gt;dw.json&lt;/strong&gt; — I&#39;d suggest creating a dedicated SFCC account/credentials with a limited access to sandboxes only, maybe DEV, but definitely not STG/PRD. It might be one shared account per project/team.&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;OCAPI Client&lt;/strong&gt; — Same here, a dedicated API Client per project with a limited access to sandboxes (and maybe DEV) only.&lt;/li&gt;
&lt;li&gt;&lt;strong&gt;3rd-party MCP Server&lt;/strong&gt; — While MCP Server from Thomas sounds reliable, it is still 3rd-party with unexpected updates. And enterprise security models can be against it. In this case we can clone it (since it&#39;s under MIT).&lt;/li&gt;
&lt;/ol&gt;
</content>
    <summary>Using an MCP Server to give AI coding assistants real SFCC context — a video walkthrough, and the security tradeoffs worth knowing before you wire one up.</summary>
  </entry>
</feed>
