Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MCP-B: A Protocol for AI Browser Automation

mcp-b.ai

Post reply on HN
Print view View original

21–30 of 200 posts

Re: MCP-B: A Protocol for AI Browser Automation

#21

Post by miguelspizza »

imcritic wrote: post #14
miguelspizza wrote: post #5

Earlier quoted context omitted.

Yup! You just declare a standard MCP server and attach a TabServerTransport to it. Any TabClientTransport in the same Tab will be able to connect to it. The examples focus mostly on extensions injecting clients at website load time, but you can ship a client with your server javascript. That being said, if the client and server live in the the same script I recommend just using the InMemoryTransports from the officia…

Wouldn't sites be able to detect presence of scripts injected by your extension (to, say, refuse you services since site owner decided they would like their site to be used only by humans, not AI agents)?

Sure. Although I'd assume if the website owner went through the hassle of creating a MCP server for their website, they would probably want to be discovered

Re: MCP-B: A Protocol for AI Browser Automation

#22

Post by rapind »

muratsu wrote: post #17

This puts the burden on the website owner. If I go through the trouble of creating and publishing an MCP server for my website, I assume that through some directory or method I'll be able to communicate that with consumers (browsers & other clients). It would be much more valuable for website owners if you can automate the MCP creation & maintenance.

I think this is the practical way. The website owner (or rather the builder, since if you're running wordpress, we can assume MCP will be part of the package) is already responsible for the human interface across many devices, and also the search engine interface (robots.txt, sitemap.xml, metatags). Having a standard we can use to curate what the AI sees and how it can interact would be hugely beneficial.

There's space for both IMO. The more generic tool that figures it out on it's own, and the streamlined tool that accesses a site's guiderails. There's also the backend service of course which doesn't require the browser or UI, but as he describes this entails complexity around authentication and I would assume discoverability.

Re: MCP-B: A Protocol for AI Browser Automation

#23

Post by miguelspizza »

TechDebtDevin wrote: post #16

hmm, I have an MCP route, that fetches the page in a browser, returns and lets the LLM inject javascript onto the page to return whatever structured output it desires..Or whatever (kinda scarily). How is this different? --Shoutout to Go-Rod https://pkg.go.dev/github.com/go-rod/rod@v0.116.2#Page

Cool, I'll check it out!

I'll need to look a bit more, but at a glance, MCP-B is more putting the onus of browser automation (i.e. how the agent will interact with the web page) on the website owner. They get to expose exactly the functionality they want to the agent

Re: MCP-B: A Protocol for AI Browser Automation

#24

Post by handfuloflight »

miguelspizza wrote: post #21
imcritic wrote: post #14

Earlier quoted context omitted.

Wouldn't sites be able to detect presence of scripts injected by your extension (to, say, refuse you services since site owner decided they would like their site to be used only by humans, not AI agents)?

Sure. Although I'd assume if the website owner went through the hassle of creating a MCP server for their website, they would probably want to be discovered

We mean if we could use this to instantiate an MCP for any website we're visiting.

Re: MCP-B: A Protocol for AI Browser Automation

#25

Post by miguelspizza »

fzysingularity wrote: post #15

The contributions for the Github project is quite intriguing: https://github.com/MiguelsPizza/WebMCP/graphs/contributors MiguelsPizza | 3 commits | 89++ | 410-- claude | 2 commits | 31,799++ | 0--

I did some git history re-visioning when I closed sourced the extension for a bit. So these are not super accurate. Claude code did write about 85% of the code though.

Re: MCP-B: A Protocol for AI Browser Automation

#27

Post by fzysingularity »

miguelspizza wrote: post #25
fzysingularity wrote: post #15

The contributions for the Github project is quite intriguing: https://github.com/MiguelsPizza/WebMCP/graphs/contributors MiguelsPizza | 3 commits | 89++ | 410-- claude | 2 commits | 31,799++ | 0--

I did some git history re-visioning when I closed sourced the extension for a bit. So these are not super accurate. Claude code did write about 85% of the code though.

Nice!

Re: MCP-B: A Protocol for AI Browser Automation

#28

Post by mfrye0 »

muratsu wrote: post #17

This puts the burden on the website owner. If I go through the trouble of creating and publishing an MCP server for my website, I assume that through some directory or method I'll be able to communicate that with consumers (browsers & other clients). It would be much more valuable for website owners if you can automate the MCP creation & maintenance.

I was thinking the same. Forward thinking sites might add this, but the vast majority of website owners probably wouldn't be able to figure this out.

Some middle ground where an agent reverse engineers the api as a starting point would be cool, then is promoted to use the "official" mcp api if a site publishes it.

Re: MCP-B: A Protocol for AI Browser Automation

#29

Post by rapind »

fzysingularity wrote: post #27
miguelspizza wrote: post #25

Earlier quoted context omitted.

I did some git history re-visioning when I closed sourced the extension for a bit. So these are not super accurate. Claude code did write about 85% of the code though.

Nice!

I was checking that out too. Looks like claude was co-author on the initial commit, which is like 90%.

https://github.com/MiguelsPizza/WebMCP/commit/26ec4a75354b1c...

Post reply on HN