Agent/Prompt Profiling

Feature request for product/service

Cursor IDE

Describe the request

I should be able to create profiles of agent settings which I can apply to any agent on demand.

for e.g. I want to build a command, but dont want to allow before every single action. So, I want to apply a setting that disables browser protection, mcp tool protection, agent mode transitions, etc on the fly only for that agent or even a prompt where I use the command.

this will ensure I’m optimally using protection settings.