I'm all in on agent-first CLIs. The CLIs I've been building have still been easier to use for me as a human than the average CLI tool. It isn't like CLIs tools have famously simple or consistent arguments from tool to tool anyway.
I find it so much more successful to have an agent interact with a CLI than an API or MCP. I can just ask: query my dev DB for an ideal URL to test a new page. It'll find the right users, resources, etc and create an excellent test URL to quickly validate the behavior of my changes. I can have it get the latest spec from Confluence, or find the latest PR build for a workitem.
If you have an API, you should really look at providing a CLI for it too.
Plugging my tools/examples:
- https://github.com/pseudosavant/confluence-fetch
agree, although the pattern I've been following is to provide a self-contained CLI for portability and usability purposes, and then an "mcp" subcommand which launches an MCP server over stdio. ultimately the "CLI" and "MCP" surfaces act as thin facades over the same functional layer.