Comment by zuzululu

No OP, but MCP really is just a logical next step once you've got an API. The API is the "low level" protocol, the MCP is the high level one, suited perfectly to an LLM that can call tools (since MCP essentially turns an API into a LLM tool).

With just an API, the agent needs to "read your API docs" to know how to call it (that can be an OpenAPI spec or even just text).

With MCP, the agent sees a bunch of tools it can call, and they've been trained to call tools so they nail it.

One more very important factor is authorization, which no one seems to mention in these discussions. CLIs were made for humans and use primitive mechanisms for authorization: either an API key you hardcode in your environment, or they literally run a background HTTP Server to get a callback OAuth call to receive a token from a browser authentication flow. Incredible that people are happy with that, appparently. With the MCP Authorization spec, you solve authorization across multiple MCP servers in the same standardized way, the LLM client you use just need to know the protocol, not how to login for every single MCP server.

Very importantly, if the MCP client does the authorization, the MCP provider has auditability: is this a call from a human or from a LLM? That's important in Enterprise! People think it's ok to let an LLM act on behalf of the human but that will eventually bite a lot of people. Did the LLM just try to hack the API while you were mindlessly clicking "yes" when it asked if you wanted to let it do something? Tough luck, there's no way to distinguish an LLM making a mistake from a human maliciously running some attack.

And as the post mentions, there's also more benefits like being able to "elicit" user input (not just request/response cycles) and the ability to have documentation and assets (skills also have this though).