<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Bedrock AgentCore on schristoph.online</title>
    <link>https://schristoph.online/tags/bedrock-agentcore/</link>
    <description>Recent content in Bedrock AgentCore on schristoph.online</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 29 Apr 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://schristoph.online/tags/bedrock-agentcore/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>MCP Sampling &amp; Elicitation: When Servers Talk Back</title>
      <link>https://schristoph.online/blog/mcp-sampling-elicitation/</link>
      <pubDate>Wed, 29 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://schristoph.online/blog/mcp-sampling-elicitation/</guid>
      <description>&lt;h2 id=&#34;from-request-response-to-collaboration&#34;&gt;From Request-Response to Collaboration&lt;/h2&gt;&#xA;&lt;figure&gt;&lt;img src=&#34;https://schristoph.online/assets/2026-04-29-mcp-sampling-elicitation-cover.png&#34;&#xA;    alt=&#34;Two entities in conversation, representing server-initiated collaboration in MCP&#34;&gt;&lt;figcaption&gt;&#xA;      &lt;p&gt;MCP evolves: servers don&amp;rsquo;t just respond anymore. They ask questions back.&lt;/p&gt;&#xA;    &lt;/figcaption&gt;&#xA;&lt;/figure&gt;&#xA;&#xA;&lt;p&gt;When I wrote about the CLI vs MCP debate [1], I focused on the infrastructure patterns underneath. But MCP itself has been evolving, and the latest additions change what&amp;rsquo;s architecturally possible.&lt;/p&gt;&#xA;&lt;p&gt;The Model Context Protocol started as a clean way for AI agents to call tools: agent sends request, server returns response. Simple, stateless, effective. But real-world agent workflows need more than request-response. They need the server to &lt;em&gt;ask questions back&lt;/em&gt;.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
