← Blogs

MCP is not dead — it is just not a personal-productivity tool

2026.08.29  ·  Draft  ·  notes on someone else's argument

The “MCP is dead” take has been circulating for a while: agents are getting good enough at using ordinary command-line tools that standing up a Model Context Protocol server for them looks like ceremony. Paul Iusztin pushed back on it this week, and his framing is the one I want to keep: the technology is not defunct, it is being evaluated against the wrong problem.

I think that is right, and I think the reason it is right is more specific than “enterprise needs governance.”

The argument, compressed

For one engineer on one laptop, a CLI genuinely wins. There is no process to run, no transport to debug, no auth to configure, no schema to keep in sync with the function it describes. The agent discovers the interface by reading --help, the same way I would. Connecting a model to Obsidian or Readwise this way is a twenty-minute job, and an MCP server for the same thing is not twenty minutes.

The counter-argument, in Iusztin's words, is to “try scaling that across a company deploying thousands of AI agents.” That is where the CLI answer stops being obviously cheaper.

What the CLI answer quietly assumes

Every argument for the CLI is load-bearing on four assumptions that hold on a laptop and fail in an organisation:

None of those survive contact with a thousand agents and several hundred people. The question stops being how does a model invoke this function and becomes where does the one true definition of this function live, and who is allowed to change it.

The real axis: who owns the tool definition

 One laptopOne organisation
Installyou, onceevery machine, forever
Update pathgit pullredeploy one server, everyone moves
Credentialsyours, already on diskheld centrally, never handed to the agent
Auditshell historya request log with an identity attached
Blast radius of a bad changeyour afternoonevery agent that calls it

Read that way, MCP is not a smarter calling convention. It is a distribution boundary — the same reason companies expose an internal service instead of letting every team write its own query against the production database. Nobody argues that HTTP APIs are dead because psql exists on your laptop. The laptop was never the case the API was built for.

The protocol question is downstream of an ownership question: how many people have to agree when this tool changes?

If the answer is one, write the CLI. If the answer is four teams and a security review, you are going to build the server eventually, and doing it late is more expensive than doing it early.

Where I would push back on both sides

Both camps are arguing about invocation. Neither is arguing about verification, which is the part I actually spend my time on.

Whether the model reaches a function through a subprocess or a JSON-RPC session, nothing in either path tells you whether calling it was the right decision. A tool call that returns 200 is not a tool call that should have happened. The failure mode I keep seeing is not a broken transport; it is an agent confidently selecting the wrong tool, or the right tool with the wrong arguments, and the plumbing dutifully reporting success.

That is a measurement problem, and it looks a lot like the offline-evaluation problems I work on elsewhere: the system scores well on the traffic it was demonstrated against and behaves differently on the traffic it did not choose.

What I would want to measure

Open questions, not conclusions. This is a first draft of a thought, written the day I read the post that provoked it.

Written against Paul Iusztin, “MCP is NOT dead… You're just using it for the wrong problem” — LinkedIn. The framing is his; the assumptions table and everything after “where I would push back” are mine.