It makes it harder for the LLM to understand what’s going on, not easier.

I’ve been wrapping the agent’s curl calls in a small cli that handles the auth but I’m wondering if other people have come up with something lighter/more portable.

This lets me add quick skills that are essentially just: “this is the OAS link, this is how you store and use the authorization, this is when I want you to use it”. That combined with pointing it at the documentation for common workflows and usage examples, and it’s been great.

The only thing I’ve had trouble with is auth really. MCPs are treated as first class citizens by most model provider’s agents and trying to provide a shell-based alternative for hiding the secret credentials from the LLM has been difficult.

I feel like this is why drugs can sometimes help with creative things, especially if you're familiar with the drug, as long as you can harness this decontextualization to put more of your focus on one thing, kind of like clearing your mind. However, its usually fruitless/harmful in anything requiring complex reasoning/judgement because it is reducing your ability to see the big picture.