MCP really only makes sense for chatbots that don’t want to have per session runtime environments. In that context, MCP makes perfect sense. It’s just an adapter between an LLM and an API. If you have access to an execution engine, then yes CLI + skills is superior.
Now you’ve replicated MCP but with extra steps and it’s harder to debug.
The agent still doesn’t have an execution environment. It can’t execute the code!
Ok, but there are still many environments where an LLM will not have access to a CLI. In those situations, skills calling CLI tools to hook into APIs are DOA.
You should watch this talk by Nicholas Carlini (security researcher at Anthropic). Everything in the talk was done with Opus 4.6:
https://www.youtube.com/watch?v=1sd26pWhfmg
Nicholas Carlini - Black-hat LLMs | [un]prompted 2026
Nicholas Carlini, Research Scientist, Anthropic, speaks at [un]prompted 2026 on: Black-hat LLMs.Large language models are now capable of automating attacks t...
YouTubeBecause not all software gets auto-updated. Most of it does not!