<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>MCP.Run.Book</title>
    <link>https://mcprunbook.com</link>
    <description>Real MCP workflows for endurance sports, built around Tredict and tested in real training.</description>
    
    <item>
      <title>Building a reusable training plan library with AI that syncs</title>
      <link>https://mcprunbook.com/posts/reusable-training-plans-claude-tredict.html</link>
      <guid>https://mcprunbook.com/posts/reusable-training-plans-claude-tredict.html</guid>
      <pubDate>Fri, 08 May 2026 00:00:00 GMT</pubDate>
      <description>How endurance coaches use AI assistants like Claude and Perplexity with the Tredict MCP Server to build a reusable training plan library that syncs structured workouts to Garmin, Coros and other watches.</description>
    </item>
    <item>
      <title>Using Perplexity&#39;s Custom Connector to Analyse Endurance Training Data</title>
      <link>https://mcprunbook.com/posts/using-perplexity-mcp-connector-with-tredict.html</link>
      <guid>https://mcprunbook.com/posts/using-perplexity-mcp-connector-with-tredict.html</guid>
      <pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate>
      <description>Perplexity as MCP client connects to external tools. See how it works with Tredict to analyse running data, determine FTP, and answer training questions with real-time web context.</description>
    </item>
    <item>
      <title>Ground contact time is speed-dependent. Here is how to normalize it.</title>
      <link>https://mcprunbook.com/posts/ground-contact-time-normalized.html</link>
      <guid>https://mcprunbook.com/posts/ground-contact-time-normalized.html</guid>
      <pubDate>Tue, 21 Apr 2026 00:00:00 GMT</pubDate>
      <description>Raw ground contact time numbers are misleading because GCT drops at higher speeds. Claude calculated a normalized efficiency value from my actual training data via the Tredict MCP Server.</description>
    </item>
    <item>
      <title>Interactive MCP Apps render real UI inside Claude and ChatGPT</title>
      <link>https://mcprunbook.com/posts/interactive-mcp-apps-tredict.html</link>
      <guid>https://mcprunbook.com/posts/interactive-mcp-apps-tredict.html</guid>
      <pubDate>Sun, 19 Apr 2026 00:00:00 GMT</pubDate>
      <description>A working example of Interactive MCP Apps, also known as ChatGPT Apps on the OpenAI side. Tredict ships two MCP tools that render actual widgets inside Claude.ai and ChatGPT, not plain text summaries.</description>
    </item>
    <item>
      <title>Claude Code with Tredict: long-running plan creation without the hangs</title>
      <link>https://mcprunbook.com/posts/claude-code-with-tredict.html</link>
      <guid>https://mcprunbook.com/posts/claude-code-with-tredict.html</guid>
      <pubDate>Tue, 14 Apr 2026 00:00:00 GMT</pubDate>
      <description>Claude.ai is great for day-to-day training questions. Claude Code in the terminal is built for long-running tasks, which turns out to matter a lot when you want a full season plan written directly into Tredict.</description>
    </item>
    <item>
      <title>Why AI training plans usually fail, and when they do not</title>
      <link>https://mcprunbook.com/posts/why-ai-training-plans-fail.html</link>
      <guid>https://mcprunbook.com/posts/why-ai-training-plans-fail.html</guid>
      <pubDate>Fri, 10 Apr 2026 00:00:00 GMT</pubDate>
      <description>Same data, same prompt, three AI assistants. Why ChatGPT and Mistral fail at training plans and what makes the difference.</description>
    </item>
    <item>
      <title>Connect Tredict to Claude, ChatGPT, Codex and Mistral via MCP</title>
      <link>https://mcprunbook.com/posts/connect-claude-to-tools.html</link>
      <guid>https://mcprunbook.com/posts/connect-claude-to-tools.html</guid>
      <pubDate>Tue, 07 Apr 2026 00:00:00 GMT</pubDate>
      <description>How to connect the Tredict MCP Server to Claude, ChatGPT, Codex and Mistral. Which client works best and why.</description>
    </item>
    <item>
      <title>What the Tredict MCP Server actually gives Claude or ChatGPT</title>
      <link>https://mcprunbook.com/posts/what-mcp-server-does.html</link>
      <guid>https://mcprunbook.com/posts/what-mcp-server-does.html</guid>
      <pubDate>Mon, 06 Apr 2026 00:00:00 GMT</pubDate>
      <description>A technical look at what data and actions Claude or ChatGPT can work with through the Tredict MCP Server, and why that changes what AI can do with training data.</description>
    </item>
    <item>
      <title>I let Claude plan my running comeback after six weeks off</title>
      <link>https://mcprunbook.com/posts/claude-with-training-data.html</link>
      <guid>https://mcprunbook.com/posts/claude-with-training-data.html</guid>
      <pubDate>Sat, 04 Apr 2026 00:00:00 GMT</pubDate>
      <description>After two colds in six weeks I used Claude and the Tredict MCP Server to get back into running. I was sceptical. After two weeks I was not.</description>
    </item>
  </channel>
</rss>
