Michael Hablich
Michael Hablich
Hmmm, in what prompts would you expect your MCP client make use of let's say select_element_visually(imageData, position) function?
In this case you still would need to match the (marked) screenshot to the actual page, which could very well have changed visually in the meantime (consider elements slightly shading...
> My thinking is that, in all scenarios where a human benefits from inspecting the DOM with that tool, an AI agent could potentially benefit as well. I think this...
> In this case you still would need to match the (marked) screenshot to the actual page, which could very well have changed visually in the meantime (consider elements slightly...
> I would just add my use case to this ticket as well - coming more from a design -, than engineering, perspective (knowledge wise). > > Using a prompts...
Relevant PR https://github.com/ChromeDevTools/chrome-devtools-mcp/pull/486. If you select an element in DevTools on the actuated page, the information which element is now also told to the AI agent. Try to use "use...
> > We are actually working on sharing context in DevTools with the MCP client :-). See [#129](https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/129) > > [#129](https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/129) would work as well, but as the title of...
Relevant: https://github.com/ChromeDevTools/chrome-devtools-mcp/issues/567
@johnhuxin can you please elaborate on your use case? How would you expect your AI agent makes use of it?
In scenarios like this I found it helpful to guide the AI agent what information it should collect e.g. in your automated regression tests tell it to: `If you encounter...