<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>MCP on yishiashia's Blog</title><link>https://yishiashia.github.io/tags/mcp/</link><description>Recent content in MCP on yishiashia's Blog</description><generator>Hugo -- gohugo.io</generator><language>zh-TW</language><copyright>Copyright © 2023 yishiashia@gmail.com. All rights reserved.</copyright><lastBuildDate>Thu, 10 Sep 2026 23:40:00 +0800</lastBuildDate><atom:link href="https://yishiashia.github.io/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>[AI 軟體工程] 授權邊界不會消失，只會上移：從 Human-in-the-loop 到 Human-on-the-loop</title><link>https://yishiashia.github.io/posts/authority-boundary-human-on-the-loop/</link><pubDate>Thu, 10 Sep 2026 23:40:00 +0800</pubDate><guid>https://yishiashia.github.io/posts/authority-boundary-human-on-the-loop/</guid><description>harness engineering 信任鏈的最後一環是 Authority（授權）。本文從 commit、push、審查與放行的邊界談起，說明薄介面不應自行擴大權限，以及如何依風險把人的注意力從 Human-in-the-loop 移到 Human-on-the-loop。</description></item></channel></rss>