I used to compare MCP and Skill in my post (AI-assisted [1]) and also maintain a CLI/MCP/Skill for YouTube.
In my opinion, MCP is not dead. "MCP Belongs to Software Engineering", it ships existing concepts from software engineering into AI. CLI, MCP-tools, and OpenAPI are interchangeable to some degree, but MCP is more than tools; there are mcp-apps[2], lazy load in context[3].
I'm wondering how they deal with AI-operated channels with non-AIG videos? I ask this because I'm the author of github.com/eat-pray-ai/yutu , which is a CLI/MCP for YouTube
There are many relay sites for AI API, which provide a much lower price compared with the original LLM provider. While the bargain does not come from nowhere, your chat history paid for it.
I'm more and more realize this since work. People wrap their solution with BIG TITLE and fancy words, while many simple but practical solutions are underestimated or not taken seriously.
I live in China, where every mobile game requires age verification. Teenagers can play for up to 1.5h/d on weekends. But as far as I can see, some parents will assist their children to unlock more time on purpose.
One reason I don't like JS or others is that they have too many ways to do the same thing, then you'll be challenged which is better and why on interview. Go offers fewer, more explicit options, not only on error handling.
In my opinion, MCP is not dead. "MCP Belongs to Software Engineering", it ships existing concepts from software engineering into AI. CLI, MCP-tools, and OpenAPI are interchangeable to some degree, but MCP is more than tools; there are mcp-apps[2], lazy load in context[3].
[1]: https://log.ifor.dev/posts/mcp_vs_skill/
[2]: https://modelcontextprotocol.io/extensions/apps/overview
[3]: https://code.claude.com/docs/en/agent-sdk/tool-search