HNHacker News
TopNewBestAskShowJobs

miguelspizza

203 karma · joined August 9, 2023

alex@mcp-b.com https://mcp-b.ai https://www.linkedin.com/in/alex-nahas/
submissionscomments
miguelspizza··on Ask HN: What are you working on? (September 2025)
I left my job to work on my side project (MCP-B: https://news.ycombinator.com/item?id=44515403) full time. I set out with the goal of making the ability to vibecode a webMCP server for your website and inject it via userscript.

While building that, I basically wrote a modern version of Tampermonkey with its own marketplace built in. So you can vibe code any userscript and publish it to the marketplace all within the extension.

The automation stuff is still the core value-prop, but this is a fun bonus feature while I work on solidifying the automation features.

I'm writing a HN post for it. Excited to show everyone in a couple weeks here.

miguelspizza··on Ask HN: Any local agents to help repetitive browser tasks?
Hey I wrote MCP-B and am about to do another launch here in a week or so. The product is a browser agent which does browser automation sudo-deterministically over WebMCP.

https://news.ycombinator.com/item?id=44515403

I’d love to give your beta access and get your thoughts if you are up to give it a run on the task you want automated.

Shoot me an email if you are interested

alex(at)mcp-b.ai

miguelspizza··on Show HN: Tsink – Embedded time-series database for Rust
Can we run it in the browser via WASM?
miguelspizza··on Claude for Chrome
The Primary client for WebMCP enabled websites is a chrome extension like Claude Chrome. So the human is still there in the loop looking at the screen. MCP also supports things like elicitation so the website could stop the model and request human input/attention
miguelspizza··on Claude for Chrome
The side-panel browser agent is a good middle ground to this issue. The user is still there looking at the website via their own browser session, the AI just has access to the specific functionality which the website wants to expose to it. The human can take over or stop the AI if things are going south.
miguelspizza··on Claude for Chrome
> It's clear to me that the tech just isn't there yet.

Totally agree. This was the thesis behind MCP-B (now WebMCP https://github.com/MiguelsPizza/WebMCP)

HN Post: https://news.ycombinator.com/item?id=44515403

DOM and visual parsing are dead ends for browser automation. Not saying models are bad; they are great. The web is just not designed for them at all. It's designed for humans, and humans, dare I say, are pretty impressive creatures.

Providing an API contract between extensions and websites via MCP allows an AI to interact with a website as a first-class citizen. It just requires buy-in from website owners.

It's being proposed as a web standard: > https://github.com/webmachinelearning/webmcp

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Sure they can inject clients, but that's really only beneficials for developers. doing it via browser extension means regular people can use it.

> It's like an OpenAPI definition but for JS/MCP?

Sortof. It's a true MCP server which you can use to expose existing (or new functionality on your webapp to the client)

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
I've thought more about this and I think the only way to make completely sure that sensitive data does not get leaked is by making sure it never makes it into the models context in the first place.

The issue is even if the MCP-B extension makes it so the user has to give confirmation when the agent want's to call a tool on a new domain after interacting with another domain, there is no clear way to determine if a website is malicious or not.

A solution to this might be to give server owners the ability to write the restricted data to extension storage on tool response instead of returning it to the models context. Instead, a reference to this location in extension storage get's passed to the model. The model then has the ability to "paste" this value into other website via tool call without ever actually seeing the value itself.

That way, MCP-B can put lots of warnings and popups when this value is requested to be shared.

Any thoughts?

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Added a summary of what has been brought up here to the repo wiki. Let me know if I missed anything

https://github.com/MiguelsPizza/WebMCP/wiki/Known-Security-I...

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Yea this is a really good idea, Maybe like a popup that say "hey x website has an MCP, do you trust it to connect?"

I guess there would also need to be a way to "audit" a websites full tool list at connection time and throw some sort of warning if tools show up that are not part of this list during use.

Interesting problems for sure. I really appreciate you taking to time to think them through. I'll call these out in the issues section of the repo

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
I see your point. The MCP-B zero config nature from a user perspective is simultaneous it's biggest strength and weakness. You can think of it kind of like putting your Social Security number into a website. You are putting a bunch of trust that they are going to protect it properly.

With MCP-B you are putting trust in both the model and the website owner. It opens up the user to risk for sure, but it's up to them to determine if the upside is worth it.

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Ah I see. Yes this is a concern, but this issue is actually not unique to MCP-B and is just a generally issue with agentic workflows that rely on a dynamic toolset from 3p vendors. (which any MCP server local or remote has the ability to be)

> With MCP-B, isn't it just automatically provided with whatever credentials are already stored in cookies/etc for a given MCP-B enabled app?

Not exactly, MCP-B just allows your extension agent to call functions that the website owner explicitly exposes. The client itself is not given an credentials like traditional MCP.

> If I load an MCP-B enabled app, does the agent automatically have access or do I have to configure it somewhere?

Theres more in the blog post but how much access the agent has and how much human approval is needed to grant this access is completely up to the website creator.

FWIW your points are valid and MCP-B should enforce some guardrails when any domain shift happens via elicitation: https://modelcontextprotocol.io/specification/draft/client/e...

I'll add it to the road map. Thanks for bringing it up!

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
ah this is a great point, I will add it to the road map
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Looks like Claude put me down as a co-author with my real name (Alex Nahas) instead of my GitHub handle (MiguelsPizza)
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Again, that's up to the website owner. They can give the model anywhere from no access to full access to the client side api.

> The agent should be treated as an untrusted user in your client, given restricted privileges scoped to only the exact access they need to perform a given task

I agree, this is exactly what MCP-B does

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Not sure I understand. The model has no more access than the user does. proper security implementation still lies with the website owner
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Ah maybe I should make that more clear. The web app is an example of a MCP-B server and the extension is a client. When you visit MCP-b.ai with the extension, it's tools will register
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Np thanks for reading! The difference is with MCP-B you don't have to integrate or maintain any AI chat functionality yourself.

It's a protocol which allows the user to bring their own model to interact with the tools on your website

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Yes it was mostly AI generated. I'm much more of a dev than a writer/marketer. Hopefully if this gains some traction I can pay someone to clean it up
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
That was everyone's first thought when MCP came out. Turns out it doesn't work too well since there is generally too many tools. People are doing interesting work in this space though
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Sorry this is in reference to the Playwright MCP server which gives a model access to screen shots of the browser and Playwright API's.

MCP-B doesn't do any DOM parsing. It exchanges data purely over browser events.

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Yea, I am planning a dev build of MCP-B which has access to user scripts apis. So technically you could `vibe code` and inject an MCP server into the target webpage
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Ah yea I'll fix that. Nice catch
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
No there is built in tool de-duping. I'm not sure how to handle domains with different url states though.

Like you said there are some edge cases where two tabs of the same website expose different tool sets or have tools of the same name but would result in different outcomes when called.

Curios if you have any thoughts on how to handle this

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Ah no, first time seeing this. How were you interacting with the website server? Via extension or some way else?
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
I think with AI tools you can pretty confidently build out an MCP server for your existing website. I plan to have good LLM docs for this very purpose.

For react in particular, lots of the form ecosystem (react hook form) can be directly ported to MCP tools. I am currently working on a zero config react hook form integration.

But yes, MCP-B is more "work" than having the agent use the website like a user. The admission here is that it's not looking like models will be able to reliably do browser automation like humans for a while. Thus, we need to make an effort to build out better tooling for them (at least in the short term)

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
Thanks! I'd be happy to help onboard. Let me know!
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
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.
miguelspizza··on MCP-B: A Protocol for AI Browser Automation
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

miguelspizza··on MCP-B: A Protocol for AI Browser Automation
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
← PreviousPage 2 of 3Next →