<?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>RPC on After the Code</title><link>https://windshock.github.io/en/tags/rpc/</link><description>Recent content in RPC on After the Code</description><generator>Hugo -- 0.145.0</generator><language>en-US</language><lastBuildDate>Thu, 07 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://windshock.github.io/en/tags/rpc/index.xml" rel="self" type="application/rss+xml"/><item><title>MCP Is Repeating the History of RPC Security</title><link>https://windshock.github.io/en/post/2026-05-07-mcp-is-repeating-rpc-security-history/</link><pubDate>Thu, 07 May 2026 00:00:00 +0000</pubDate><guid>https://windshock.github.io/en/post/2026-05-07-mcp-is-repeating-rpc-security-history/</guid><description>MCP security risks are not about prompt injection. They stem from the same configuration-to-execution escalation pattern that has plagued RPC, local security software, and CI/CD pipelines for decades.</description></item></channel></rss>