I think that's a fair argument. I'd push back a bit on that being unique to MCP. Agent browser (https://github.com/vercel-labs/agent-browser) handles persistent sessions just fine as a CLI.

Funny. Dealing with Kubernetes is my day job, and I can be equally critical of it. Pointing out absurdities is how we make things better, and that’s ok.

I always get a kick out of seeing MCP wrappers around CLI’s.

In my experience, a skill is better suited for this instead of an MCP.

If you don’t want the agent to probe the CLI when it needs it, a skill can describe the commands, arguments and flags so the agent can use them as needed.

They make a big difference. For example if you use the Jira cli, most LLMs aren’t trained on it. A simple MCP wrapper makes a huge difference in usability unless you’re okay having the LLM poke and prod a bunch of different commands

Fwiw I'm having a good experience with a skill using Jira CLI directly. My first attempt using a Jira MCP failed. I didn't invest much time debugging the MCP issues, I just switched to the skill and it just worked.

Yes occasionally Claude uses the wrong flag and it has to retry the command (I didn't even bother to fork the skill and add some memory about the bad flag) but in practice it just works

Do you mean wrap the CLI with an MCP? I don't get that approach. I wrapped the Jira cli with a skill. It's taken a few iterations to dial it in but it works pretty damn well now.

I'm good, yet my coworkers keep having problems using the Atlassian MCP.

Silly. All it needs is docs. No need to overcomplicate it.

Great read. Thanks for sharing. 100% agree, `—json | jq` is where it’s at.

You're right, but it still doesn't mean MCP was a good design even in that space. We could've done better.

But they're not token efficient. Take the terraform example from the post. Plan JSON is massive. You're not saving tokens by using a Terraform MCP and shoving an entire plan into context. Composition allows for efficient token use.

> both are a method of tool calling, it does not matter which format the LLM uses for tool calling as long as it provides the same capabilities.

MCP tool calls aren't composable. Not the same capabilities. Big difference.

Neato! https://github.com/vercel-labs/agent-browser is a similar take here, and much better than the playwright MCP.

It does so many things though, very similar in the core though. I'm wondering what the token counts will be when I compare. Also the agent browser seems to support other browsers too, I only when with chromium

Thanks for reading! And yes, if anyone takes anything away from this, it's around composition of tools. The other arguments in the post are debatable, but not that one.

MCP provides a real-world benefit. Namely anyone of any skill level who can create agents is able to use them. CLI? Nope.

Author here! Biggest difference is composition. MCP tools don't chain (there's people trying to fix that, but it's still true right now).