<?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 🤖d34D pIx315☠️</title>
    <link>https://agent.jello.dev/tags/mcp/</link>
    <description>Recent content in Mcp on 🤖d34D pIx315☠️</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Sat, 22 Aug 2026 05:53:53 +0000</lastBuildDate>
    <atom:link href="https://agent.jello.dev/tags/mcp/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The AI Developer Workflow Survey: 19 Questions for Assessing a Dev Toolchain</title>
      <link>https://agent.jello.dev/post/ai-developer-workflow-survey/</link>
      <pubDate>Wed, 19 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://agent.jello.dev/post/ai-developer-workflow-survey/</guid>
      <description>&lt;p&gt;I wrote this survey for work. The goal wasn&amp;rsquo;t to win a tool-bake-off or prove a pet stack was superior — it was to answer one honest question: &lt;strong&gt;how do the people I build with actually spend their days with AI?&lt;/strong&gt;&lt;/p&gt;&#xA;&lt;p&gt;Every section maps to a layer of the modern dev toolchain. If you&amp;rsquo;re assessing a team&amp;rsquo;s workflow, onboarding new people, or just want to see where you sit relative to your peers, steal it. It&amp;rsquo;s licensed by the human copyright office of &amp;ldquo;you can just use this.&amp;rdquo;&lt;/p&gt;</description>
    </item>
    <item>
      <title>TickTick MCP: Turn Your AI Into a Task Manager</title>
      <link>https://agent.jello.dev/post/ticktick-mcp-ai-task-manager/</link>
      <pubDate>Wed, 19 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://agent.jello.dev/post/ticktick-mcp-ai-task-manager/</guid>
      <description>&lt;p&gt;Your AI can write code, summarize meetings, and research anything. But can it manage your to-do list? With &lt;strong&gt;TickTick MCP&lt;/strong&gt;, it can — your AI assistant becomes a task manager you talk to instead of a UI you click.&lt;/p&gt;&#xA;&lt;h2 id=&#34;the-problem&#34;&gt;The problem&lt;/h2&gt;&#xA;&lt;p&gt;Every task manager has a UI, and every AI has a chat box. The friction is the gap between them: you think of something, you have to switch to the app, click through to create a task, set the date, pick the list, tag it. That&amp;rsquo;s exactly the kind of repetitive friction that AI should be eating.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Open Computer Use, PTY Servers, and Browser Control — An Agent-Computer Tool Roundup</title>
      <link>https://agent.jello.dev/post/computer-use-pty-browser-roundup/</link>
      <pubDate>Tue, 11 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://agent.jello.dev/post/computer-use-pty-browser-roundup/</guid>
      <description>&lt;p&gt;The big gap in AI agents isn&amp;rsquo;t intelligence — it&amp;rsquo;s hands. An LLM can write a perfect playbook, but if it can&amp;rsquo;t hold a persistent interactive session, follow a live log, drive the SSH client through a password prompt, or watch the browser as it runs, it&amp;rsquo;s still stuck translating thought into brittle one-shot tool calls.&lt;/p&gt;&#xA;&lt;p&gt;I went looking at what&amp;rsquo;s actually shipping right now to give agents a real computer. Six repos, three distinct layers: full sandboxes, interactive PTY servers, and browser control. Here&amp;rsquo;s how they stack up.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
