
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Agentailor</title>
      <link>https://blog.agentailor.com/blog</link>
      <description>In-depth guides on building AI agents, for developers — from the agent loop and core primitives to LangGraph, MCP, coding agents, open-source agents, and managed services. Working code in every article.</description>
      <language>en-us</language>
      <managingEditor>undefined (Ali Ibrahim)</managingEditor>
      <webMaster>undefined (Ali Ibrahim)</webMaster>
      <lastBuildDate>Sat, 03 Oct 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://blog.agentailor.com/tags/webmcp/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://blog.agentailor.com/blog/before-you-add-webmcp</guid>
    <title>Before You Add WebMCP: the Security Problem Nobody&#39;s Selling You</title>
    <link>https://blog.agentailor.com/blog/before-you-add-webmcp</link>
    <description>WebMCP lets a web page hand tools to AI agents, and most coverage sells it as your website becoming an API. The spec, WebKit, and even ChatGPT say something the pitch leaves out: an agent cannot verify what a page tool does, and it runs with your users logged-in session. I shipped both sides of WebMCP on Agentailor, red-teamed them, and deleted one. Here is what that taught me.</description>
    <pubDate>Sat, 03 Oct 2026 00:00:00 GMT</pubDate>
    <author>undefined (Ali Ibrahim)</author>
    <category>WebMCP</category><category>MCP</category><category>Security</category><category>AI Agents</category>
  </item>

    </channel>
  </rss>
