4 posts tagged with "Claude Code"

TL;DR​

• The Remote Browser gives your agent a hosted Chrome session — navigate, click, scroll, snapshot, and fill forms from Claude Code or Cursor without installing Playwright or opening a local browser.
• Remote Browser is already a top-twenty MCPBundles bundle — one of the connectors operators reach for most often in production.
• A real paying customer ran 100+ browser steps on day one after finding us on the skills page: contractor directory, listing by listing, snapshot and summarize, next page. That's the workflow we hardened in July.

Someone signed up for Starter, connected Remote Browser from our skills page, and spent the afternoon doing serious work — not kicking tires. Before dinner they'd issued more than a hundred successful navigate-and-click commands through Claude Code: open a contractor directory, drill into a listing, snapshot the page, ask for a summary, move to the next result, keep going. No local Chrome. No Playwright install. Just chat driving a live cloud browser through a real research job.

That session is why we cared about multi-page reliability. Remote Browser isn't for a single hero screenshot — it's for afternoons like that: vendor comparisons, signup walkthroughs, paginated directories, deploy spot-checks, one session carrying the whole tour.

Connect once, describe the journey in plain language, and let the agent keep working in the same session while it moves through the site.

You can now ask Claude Code or Cursor to record a screen video of a website tour — open a page, scroll, move to the next page, scroll again — and hand you back an MP4. The whole thing runs in a cloud Chrome session. There is nothing to install: no browser on your machine, and no screen-capture app running in the background.

This started as a question — can we clip video from the remote browser instead of the local one? — and turned into a capability we think a lot of people will reach for: a demo/tour video of any live site, driven entirely from the agent you already work in.

Every Model Context Protocol server on the internet is, at the end of the day, a URL. The hard question is which AI tool you're going to plug it into — and the honest answer is that the experience varies wildly depending on which app you live in.

I run MCPBundles, so I see what users actually do after they generate an MCP URL. A lot of them sign up, get the URL, then bounce because the next step — wiring it into the tool they actually use — is unfamiliar territory. Sometimes that's our fault for not making it obvious. Sometimes the tool's setup flow is genuinely awkward. And sometimes the tool literally hides MCP behind a developer toggle that nobody told you to flip.

This is the field report I'd write a friend who asked me, today, "which AI tool should I use if I want MCP to actually work?" Frank, opinionated, with the quirks named.

Claude Code ships with built-in MCP (Model Context Protocol) support. Add external tools — databases, APIs, SaaS platforms — directly from the terminal with claude mcp add. This page covers every command, config option, and common fix.