Being able to plug MCPs into my desktop Claude app has been awesome. I gave it a K/V store and access to my project folder and it uses the tools very well with minimal guidance.
Today there's no way I can talk an average person into getting MCP working without them having to modify some config files hidden away somewhere.
I would bet big money that as soon as Claude and ChatGPT add 1 click "app store" experiences everyone will be using them in a week.
It is not easy to "just" use an API as a human, plus a lot of APIs force you to deal with tokens and storing+executing code. In some cases it's easier for the LLM to simply fetch or curl basic APIs directly than waste context tokens on the overhead of an MCP tool call (e.g. all these weather tool examples), but with MCP consistency is much better, so depending on the use case MCP vs API both have advantages.
Since my comment is already pretty long: LLM+RSS+Fetch is a killer combination for me, and it's almost all off the shelf these days. Once I add an RSS merge tool I think it will be an excellent way to consume content.
Today there's no way I can talk an average person into getting MCP working without them having to modify some config files hidden away somewhere.
I would bet big money that as soon as Claude and ChatGPT add 1 click "app store" experiences everyone will be using them in a week.
It is not easy to "just" use an API as a human, plus a lot of APIs force you to deal with tokens and storing+executing code. In some cases it's easier for the LLM to simply fetch or curl basic APIs directly than waste context tokens on the overhead of an MCP tool call (e.g. all these weather tool examples), but with MCP consistency is much better, so depending on the use case MCP vs API both have advantages.
Since my comment is already pretty long: LLM+RSS+Fetch is a killer combination for me, and it's almost all off the shelf these days. Once I add an RSS merge tool I think it will be an excellent way to consume content.