Let your Coding Agent debug the browser session with Chrome DevTools MCP

Re:Let your Coding Agent debug the browser session with Chro... by tonyhschu on Sunday March 15, 2026 @04:53PM (#47391775)

Very cool. I do something like this but with Playwright. It used to be a real token hog though, and got expensive fast. So much so that I built a wrapper to dump results to disk first then let the agent query instead. https://uisnap.dev/

Will check this out to see if they’ve solved the token burn problem.

[ Parent | on HN ]

Re:Let your Coding Agent debug the browser session with Chro... by Torn on Sunday March 15, 2026 @06:00PM (#47392410)

Mostly, yes: https://github.com/microsoft/playwright-cli

[ Parent | on HN ]

Re:Let your Coding Agent debug the browser session with Chro... by mambodog on Sunday March 15, 2026 @06:18PM (#47392567)

my workaround for this was to make a wrapper mcp server which uses claude haiku to summarize the page snapshot returned in the response of each playwright mcp call, and that has worked pretty well for me: https://github.com/jsdf/playwright-slim-mcp

[ Parent | on HN ]

Re:Let your Coding Agent debug the browser session with Chro... by esperent on Sunday March 15, 2026 @10:01PM (#47394277)

I use playwright CLI. Wrote a skill for it, and after a bit of tuning it's about 1-2k context per interaction which is fine. The key was that Claude only needs screenshots initially and then can query the dev tools for logs as needed.

[ Parent | on HN ]