作为一个社区，我们需要明白 MCP 是不需要的。
2 分•作者: Lethalman•3 个月前
1. 为你的 AI 客户端提供一个“curl”封装器，用于验证允许访问的 API 方法和端点。
2. 告诉你的 AI 下载网页文档，并使用 html2text + grep + head + tail 来发现它需要的内容。
说真的，这真的有效。无需每个人都重新发明自己的 MCP 服务器。无需每次都在提示中放入你的整个文档。只需改进你已有的内容：
* 为你的 API 端点添加 OAuth2，并改进你的文档。
* 对于 CLIs，无需将你的整个帮助信息复制粘贴到 SKILLS 中，只需改进你现有的 --help 即可。
如果非 AI 用户使用和理解起来更容易，那么对 AI 本身也更好，不要重复工作。
上面第 1 点绝对需要某种协议，但不需要用托管在某处的语言编写整个 MCP 服务器。只需一个 JSON 文件就足够了，AI 客户端可以下载它，用户可以选择允许使用哪一组方法/端点（只读、写入、管理）。这不需要放在提示中，它是在验证 HTTP 调用。可以在提示中放入的最多只是例如“只允许只读端点”之类的提示，给 AI 一个提示。就这些！
查看原文
1. Give your AI client a wrapper to "curl" that does validation of what API methods and endpoints is allowed to hit<p>2. Tell your AI to download web docs and use html2text + grep + head + tail to discover what it needs.<p>Seriously, it just works. No need for everyone to reinvent its own MCP server. No need to put your whole documentation every time in the prompt. Just improve what you have:<p>- Add OAuth2 to your API endpoints, and improve your docs.<p>- For CLIs, no need to copy paste your whole help into SKILLS, just improve your existing --help.<p>If things get easier to use and understand for non-AI, then it's also better for AI itself, don't duplicate work.<p>Point 1) above definitely needs some kind of protocol, but not a whole MCP server written in a language hosted somewhere. Just a json is enough that an AI client downloads and the user can select which group of method/endpoint is allowed (Read-only, Write, Admin). THIS DOES NOT need to go in the prompt, it's validating the http calls. What can go in prompt is just e.g. at most "Only read-only endpoints are allowed" to give a hint to the AI. That's it!