Hacker News Reader

Comment by cookiengineer | Hacker News Reader

I've been following your progress for a while now and I'm super impressed how far you've got already.

Are you working on unifying the tools that the LLM uses with the MCP / model context protocol?

As far as I understand, lots of other providers (like Bolt/Stackblitz etc) are migrating towards this. Currently, there's not many tools available in the upstream specification other than File I/O and some minor interactions for system-use - but it would be pretty awesome if tools and services (like say, a website service) could be reflected there as it would save a lot of development overhead for the "LLM bindings".

Very interesting stuff you're building!

View on HN

hmm, I though about this a lot. But tbh I think MCP is sort of a gimmick... probably the better way is for agents just to understand the http apis directly. Maybe I'm wrong, very happy to be convinced differently. Do you think MCP server for the cloud version would be useful?

strong agree with this -- I don't understand outside of integration with Claude Desktop why to use MCP rather than a dedicated API endpoint.

What’s your take - how can we expose Browser Use to as many use cases as possible? Is there easier way than openapi config?

I want to use browser-use in Cursor but I am using another option because it doesn't support MCP integration which is the common language they support for external tools

I believe MCP helps here because it standardizes integrations, enhances user control via opt-in plugins, and improves security by avoiding direct endpoint calls.

@gregpr07 wouldn't adoption of MCP open up Browser-use to more use cases?

It probably would yeah. I was very against it but this HN post sorta points me to “people want mcp”

Hmm, I don't mean this negatively, but MCP is mentioned only in this thread and 2 comments up you say 'I thought about this a lot' and now you are convinced based on 2 people saying they would like it? Isn't standardising something people want always? And MCP seems to have easily won that 'battle' user wise -> what have you been thinking about exactly?

as building blocks we of course prefer APIs. However, interfacing directly with the browser (or desktop) can enable end users to do way more things without having integration built by devs, in theory at least. In reality, LLM may not have reached that point yet and there are security concerns.

MCP seems nicer than requiring LLM hosts execute arbitrary curl calls to endpoints since it packages a tool into a dedicated plugin that users can opt into.

E.g. this puppeteer MCP: https://x.com/windsurf_ai/status/1894553166609617032

You can write a wrapper to use it with MCP, or use one someone else has created:

https://github.com/Saik0s/mcp-browser-use/blob/main/README.m...

Reply on news.ycombinator.com