Show HN：两周编码，三个月 OpenAI 审核，我的 ChatGPT 应用上线了
4 分•作者: Aldipower•3 个月前
我运营 Tredict，这是一个耐力运动训练平台，自 2020 年以来我一直在构建它。OpenAI 在 12 月向第三方开放了 ChatGPT App Directory，官方 Tredict 应用现已上线。实际编程花了两个星期，但整个过程花了三个月。
关于向 OpenAI 提交申请的流程（时间线、审核工作、他们要求的内容），我如何在 iframe 小部件中解决用户身份验证内容，或者为什么我不得不删除某些工具以保持在 OpenAI 健身/健康领域的讨论，欢迎提问。
[https://www.tredict.com/blog/tredict_chatgpt_app/](https://www.tredict.com/blog/tredict_chatgpt_app/)
只需点击几下，即可连接免费的 ChatGPT 帐户，然后让 ChatGPT 分析您的活动、重命名过去的训练，或创建结构化训练计划。计划好的训练会通过 Tredict 同步到 Garmin、Coros、Wahoo、Suunto 等设备。当您提出要求时，一个交互式的 Tredict 视图会直接在聊天线程中打开，显示带有图表、地图和指标的实际活动，或您刚刚创建的结构化训练计划。
我发现这有两点很有趣：
该应用使用 MCP UI Apps，而不仅仅是工具。Tredict 的实际活动和计划视图在聊天中呈现为交互式小部件。到目前为止，我见过的大多数 ChatGPT 应用都仅限于工具，小部件模式仍然不常见。将用户身份验证内容放入这些小部件是最难的部分。小部件在沙盒化的 iframe 中运行，无法访问用户的 OAuth 令牌，而且目前基本上没有关于此的已记录的最佳实践。
ChatGPT 在其上下文窗口方面也很节俭，因此它倾向于获取活动列表并跳过详细指标，除非您提示它。一个模糊的“告诉我关于我的跑步”会得到一个肤浅的答案，而“获取详细信息并给我一个详细的评估”会得到完整的分析。对于创建多周计划，使用相同的 MCP 服务器的 Claude 仍然表现得更好。使用 Claude.ai，我可以构建跨越数周甚至数月的完整结构化训练计划，具有适当的周期化、混合运动类型和基于过去活动数据的个性化间歇训练。ChatGPT 在这个范围内很吃力。限制在于主机，而不是服务器。交互式 MCP UI Apps 也在 Claude.ai 中运行，因此相同的活动和计划小部件也会直接在那里呈现。
服务器位于 [https://www.tredict.com/api/mcp/v2](https://www.tredict.com/api/mcp/v2)，并与任何兼容 MCP 的主机一起使用。老实说，它与 Claude.ai 配合得最好，这使得我申请在 Anthropic 的连接器目录中列出的申请一直处于待处理状态而没有反馈，这有点荒谬。如果任何 Anthropic 的人看到了这篇文章：真的非常感谢状态更新，甚至是被拒绝并说明原因。
查看原文
I run Tredict, an endurance sports training platform I've been building since 2020. OpenAI opened the ChatGPT App Directory to third-party submissions in December, and the official Tredict app is now live. The actual programming took me two weeks, but the entire process took three months.<p>AMA on the submission process to OpenAI (timeline, review effort, what they ask for), how I solved user-authenticated content inside the iframe widgets, or why I had to remove certain tools to stay on the fitness side of OpenAI's fitness/health line.<p><a href="https://www.tredict.com/blog/tredict_chatgpt_app/" rel="nofollow">https://www.tredict.com/blog/tredict_chatgpt_app/</a><p>Connect with a free ChatGPT account in a couple of clicks, then ask ChatGPT to analyse your activities, rename past sessions, or create structured workouts. Planned workouts sync to Garmin, Coros, Wahoo, Suunto and some more via Tredict. When you ask for it, an interactive Tredict view opens directly in the chat thread, showing the actual activity with charts, map and metrics, or the structured workout you just created.<p>Two things I find interesting about this:<p>The app uses MCP UI Apps, not just tools. Tredict's actual activity and plan views render inside the chat as interactive widgets. Most ChatGPT apps I've seen so far are tool-only, the widget pattern is still uncommon. Getting user-authenticated content into those widgets was the hardest part. The widget runs in a sandboxed iframe that has no access to the user's OAuth tokens, and there are basically no documented best practices for this yet.<p>ChatGPT is also frugal with its context window, so it tends to fetch the activity list and skip the detailed metrics unless you nudge it. A vague "tell me about my run" gets a shallow answer, while "fetch the details and give me a detailed assessment" gets the full analysis. For multi-week plan creation Claude with the same MCP server still works noticeably better. With Claude.ai I can build full structured training plans spanning weeks or even months, with proper periodisation, mixed sport types and individualised intervals based on past activity data. ChatGPT struggles with that scope. The limit sits with the host, not the server. The interactive MCP UI Apps also work in Claude.ai, so the same activity and plan widgets render directly in the chat there too.<p>Server lives at <a href="https://www.tredict.com/api/mcp/v2" rel="nofollow">https://www.tredict.com/api/mcp/v2</a> and works with any MCP-compatible host. Honestly it works best with Claude.ai, which makes it slightly absurd that my application to be listed in Anthropic's connector directory has been pending without feedback for a while. If any Anthropic folks see this: would genuinely appreciate a status update or even a rejection with reason.