I am trying to figure out how Cursor can read logs from Firefox’s inspector console directly, perhaps using an MCP server.
Has anyone managed this?
1 Like
You should be able to do this with MCP - there’s also a community project called cursor-tools that implements this without MCP. While we don’t officially support this functionality, we are thinking about this as a built in feature for the future!
2 Likes
please please please consider seriously adding the ability for Cursor to at least read the Chrome Browser Log and Network tab (screenshots would be a nice-to-have also)
1 Like
We’re actively looking into adding browser dev tools integration - its an obvious feature I think Cursor would benefit from, just need to make sure we implement it in a secure way.
4 Likes
That’s awesome to hear - thank you for taking the time to reply and let us know this is cooking! 
I’m eagerly awaiting this implementation, as it would massively speed up workflow (as you already know) 
A MCP exists to interact with the site: GitHub - executeautomation/mcp-playwright: Repository contains Playwright Model Context Protocol to automate Browser and APIs
Personally I haven’t got it to work. Right now I find MCPs unstable in cursor. However, it’s actually kind of useless right now since it can only write to the console. So you use it primarily for navigating the site. Using Claude, I couldn’t read the console logs.
Like danperk mentioned, you can use cursor-tools, and in theory, you should be able to open up a chrome instance and do "cursor-tools browser extract --network --console —connect-to reload-current to read the console logs of a running instance, but I couldn’t get it to work and it seemed like a clumsy way of doing it. Other wise you just have to open up a headless browser every time you want to check the console logs, which seems inefficient.
There is a recent cursor extension that aims to do this: GitHub - saketsarin/composer-web: Cursor extension that forwards frontend errors and screenshots to composer in one-click, making development seamless for you
But it’s very early in development and I couldn’t get it to work, and it seems to me the approach isn’t ideal.
The best way I got it to work is to create a little javascript file that listens to a chrome debugger instance via websockets. When the composer agent runs it, it can get live access because the terminal content will be added to the context of the composer.
I made thread showing it here: Tutorial: Supercharged Cursor composer agent with Chrome DevTools
You can also try this which works pretty well for me but the setup is bit complex.