You don't need MCP if you can instead drop in a skill markdown file that says "to access the GitHub API, use curl against api.github.com and send the GITHUB_API_KEY environment variable in the authorization header. Here are some examples. Consult github-api.md for more."

Am I the only person left that is still impressed that we have a natural language understanding system so good that its own tooling and additions are natural language?

I still can't believe we can tell a computer to "use playwright Python to test this new feature page" and it will figure it out successfully most of the time!

Impressing, but I can't believe we went from fixing bugs to coffee-grounds-divination-prompt-guessing-and-tweaking when things don't actually go well /s

> You don't need MCP

Depends on who the user is...

A difference/advantage of MCP is that it can be completely server-side. Which means that an average person can "install" MCP tools into their desktop or Web app by pointing it to a remote MCP server. This person doesn't want to install and manage skills files locally. And they definitely don't want to run python scripts locally or run a sandbox vm.

That's going to be a lot less efficient context-wise and computing-wise than using either a purpose-built MCP or skill based around executing a script.

I would much, much rather provide discreet APIs directly to the LLM via MCP than just tell it to hit the api and figure it out from the docs.

Strong agree here