[lxe]

It uses ariaSnapshot, which is an accessible representation of the DOM used by screen readers and accessibility validation tools as well as playwright testing.

However, even with that, it will quickly exhaust the model context if you navigate to something like Gmail. I just verified this with cursor.

I've been playing around with a much better textual representation of the page that's much more compact:

https://github.com/lxe/chrome-mcp/blob/master/src/runtime-te...

This uses your own chrome session and doesn't require a huge context size.

I might refactor this to use the aria interface available to the CDP, which I wasn't aware of at the time.

[dannyobrien]

I agree -- I hacked up a CDP-driven MCP so that Claude can drive your own browser instance, and I think that's more in the spirit of how MCP is supposed to work (where it's driving your tools under supervision, rather than spinning up its own context)