It seems that the author thinks that AI use is limited to developers, I don't understand how short slighted is the debate between CLI and MCP. Sure, CLI are more convenient, but currently most AI users consume LLM through online tools like ChatGPT
A basic example: a company using ChatGPT or Claude, and wanting to connect their business tools (ex: marketing, sales, project management...). in that case MCP is perfect from an enterprise point of view, and the integration can be managed at the company level.
This. I work with lots of business users who don't even know what a CLI is. They just want company apps to be connected to a (secure/managed) LLM and interact with those apps via a chat interface. So, MCP definitely has a place for the overwhelming majority of knowledge workers who aren't tech-savvy like developers.
Skills + CLI let companies describe exactly how the tool should be used (for example, JIRA MCP just exposes functions, JIRA skill can say, "I'm in the finance team, my project space is FIN-, if you create a ticket, use that." and then expose the same jira cli.
A basic example: a company using ChatGPT or Claude, and wanting to connect their business tools (ex: marketing, sales, project management...). in that case MCP is perfect from an enterprise point of view, and the integration can be managed at the company level.