Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code • Hacker News Board

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#121

Post by taberiand » Tue, Apr 08, 2025, 12:33 AM UTC

throwaway314155 wrote: post #104

oulipo wrote: post #101

Earlier quoted context omitted.

It's just a way to provide a "library of methods" / API that the LLM models can "call", so basically giving them method names, their parameters, the type of the output, and what they are for, and then the LLM model will ask the MCP server to call the functions, check the result, call the next function if needed, etc Right now if you go to ChatGPT you can't really tell it "open Google maps with my account, search for…

> with a "browser MCP" it is now possible: ChatGPT has a way to tell your browser "open Google maps", "show me a screenshot", "click at that position", etc It seems strange to me to focus on this sort of standard well in advance of models being reliable enough to, ya know, actually be able perform these operations on behalf of the user with any sort of strong reliability that you would need for widespread adoption to…

I think MCPs compensate for the unreliability issue by providing a minimal and well defined interface to a controlled set of actions. That way, the llm doesn't have to be as reliable thinking what it needs to do and in acting, just in choosing what to do from a short list.

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#122

Post by hedgehog-ai » Tue, Apr 08, 2025, 12:35 AM UTC

StevenNunez wrote: post #94

I feel like I slept for a day and now MCPs are everywhere... I don't know what MCPs are and at this point I'm too afraid to ask.

I know what you mean, I think MCP is being widely adopted but it's not grassroots.. its a quick entry to this market by an established AI company trying to dominate the mind/market share of developers before consensus can be reached developers.

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#123

Post by mgraczyk » Tue, Apr 08, 2025, 12:39 AM UTC

Gehinnn wrote: post #69

Would be nice if it could use the Accessibility Tree from chrome dev tools to navigate the page instead of relying on screenshots ( https://developer.chrome.com/blog/full-accessibility-tree )

In fact you have it backwards. It has no screenshots at the moment, only the accessibility tree

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#124

Post by marifjeren » Tue, Apr 08, 2025, 1:13 AM UTC

pavelfeldman wrote: post #119

I mean no disrespect, but this looks like an outdated clone of https://github.com/microsoft/playwright-mcp https://github.com/microsoft/playwright-mcp/blob/main/src/to... https://github.com/BrowserMCP/mcp/blob/main/src/tools/tool.t...

From the Browser MCP README.md:

> Credits: Browser MCP was adapted from the Playwright MCP server

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#125

Post by doug_life » Tue, Apr 08, 2025, 1:13 AM UTC

This may be obvious to most here, but you need Node.js installed for the MCP server to run. This critical detail is not in the set up instructions.

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#126

Post by acedTrex » Tue, Apr 08, 2025, 1:15 AM UTC

XCSme wrote: post #113

acedTrex wrote: post #111

Earlier quoted context omitted.

The speed that every major LLM foundational model provider has jumped on this bandwagon feels VERY artificial and astro turfy...

Maybe because the LLM improvements haven't been that good in the last year, they needed some new thing to hype it/market it. EDIT: Don't get me wrong, the benchmark scores are indeed higher, but in my personal experience, LLMs make as many mistakes as they did before, still too unreliable to use for cases where you actually need a factually correct answer.

This is in my opinion exactly what it is. A bunch of people throwing stuff at the wall trying to show "impact."

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#127

Post by JackYoustra » Tue, Apr 08, 2025, 1:15 AM UTC

PantaloonFlames wrote: post #86

JackYoustra wrote: post #80

Earlier quoted context omitted.

MCP is useful because anthropic has a disproportionate share of API traffic relative to its valuation and a tiny share of first-party client traffic. The best way around this is to shift as much traffic to API as possible.

First party client , meaning browser? User agent or … Electron app, or , any mobile app?

first party client as in a claude subscription will give you access (mostly app + web)

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#128

Post by mattfrommars » Tue, Apr 08, 2025, 1:20 AM UTC

oulipo wrote: post #101

StevenNunez wrote: post #94

I feel like I slept for a day and now MCPs are everywhere... I don't know what MCPs are and at this point I'm too afraid to ask.

It's just a way to provide a "library of methods" / API that the LLM models can "call", so basically giving them method names, their parameters, the type of the output, and what they are for, and then the LLM model will ask the MCP server to call the functions, check the result, call the next function if needed, etc Right now if you go to ChatGPT you can't really tell it "open Google maps with my account, search for…

Isn't the idea of AI agent talking to each by telling LLM model to reply say in, JSON and with some parameter value map to, say function in Python code? That in retrospect, given context {prompt} to LLM will be able to call said function code?

Is this what 'calling' is?

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#129

Post by willsmith72 » Tue, Apr 08, 2025, 1:25 AM UTC

dalemhurley wrote: post #99

tempoponet wrote: post #84

Earlier quoted context omitted.

Modern captchas use a number of tools including many of the approaches you mentioned. This why you might sometimes see a CloudFlare "I am not a robot" checkbox that checks itself and moves along before you have much time to even react. It's looking at a number of signals to determine that you're probably human before you've even checked the box.

When I am using keyboard navigation, shortcuts and autofills, I seem to get mistaken for a bot a lot. These Captchas are really bad at detecting bots and really good at falsely labelling humans as bots.

Well you have to have false positives or negatives. Maybe they prefer positives

Re: Show HN: Browser MCP – Automate your browser using Cursor, Claude, VS Code

#130

Post by SubiculumCode » Tue, Apr 08, 2025, 1:27 AM UTC

omgwtfbyobbq wrote: post #75

SSLy wrote: post #68

Earlier quoted context omitted.

it does, CF bans my own honest to God clicks if I do them too fast.

About five years ago, maybe more, Google started sending me captchas if I ran too many repetitive searches. I could be wrong, but it feel like most large platforms have fairly sophisticated anti-bot/scraping stuff in place.

Google does the same to me: Don't they know, I keep modifying my searches because their results sucked so bad I had to try 30 times to find the piece of information I needed?