<?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 George Kanellopoulos</title><link>https://gkanellopoulos.com/tags/mcp/</link><description>Recent content in Mcp on George Kanellopoulos</description><generator>Hugo</generator><language>en-us</language><copyright>Copyright © 2026, George Kanellopoulos.</copyright><lastBuildDate>Thu, 02 Jul 2026 10:00:00 +0200</lastBuildDate><atom:link href="https://gkanellopoulos.com/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>The Effective Agent</title><link>https://gkanellopoulos.com/ai-in-the-enterprise/the-effective-agent/</link><pubDate>Thu, 02 Jul 2026 10:00:00 +0200</pubDate><guid>https://gkanellopoulos.com/ai-in-the-enterprise/the-effective-agent/</guid><description>Agentic AI is the most hyped and least operationalized technology of 2026: 79% of organizations report adopting AI agents, yet only 11% have solutions in production. This white paper examines why, through the anatomy of a production harness, the architecture patterns that survive contact with reality, the ways agents fail differently than traditional software, and the governance, economics and organizational readiness that determine who closes the gap. It ends with ten recommendations for technical leadership.</description></item><item><title>Tool Metadata Poisoning: An Unresolved Attack Surface in MCP</title><link>https://gkanellopoulos.com/ai-in-the-open/tool-metadata-poisoning-ctms/</link><pubDate>Thu, 02 Apr 2026 10:00:00 +0200</pubDate><guid>https://gkanellopoulos.com/ai-in-the-open/tool-metadata-poisoning-ctms/</guid><description>Nothing verifies that a tool&amp;rsquo;s description is what its publisher wrote, and researchers have repeatedly demonstrated poisoning attacks against MCP clients. CTMS is a signing and verification scheme that prevents these attacks at runtime.</description></item></channel></rss>