I can speak for Chrome's MCP which I have more experience.
devtools MCP will have access to more deep level fetures such as performance profiling, lighthouse and network requests in details.
For example, I had success using chrome devtools mcp to debug frontend performance issues. The LLM captured and analyzed some nice traces and was able to spot bottlenecks and unnecessary repaints and reflows.
All this felt heavy to me. Full browser, debug protocol, DOM dump on every read. MCP vs CLI is the smaller question, what sits underneath matters more. So I built a small Rust binary that drives the system webview directly and returns state tokens and deltas instead of the DOM. Loading the HN front page costs the agent about 50 tokens. It speaks both MCP and CLI, pick whichever your agent prefers.
> How do you test on Safari if you don’t have Apple devices?
How do you test a Playstation game without a Playstation (dev kit)? How do you test some hardware firmware without having the hardware? How can you run a program without the hardware required to run the program, if no emulator/simulator is available?
I'm almost lost at words how these are questions, unless they're theoretical and some diatribe comes afterwards that has the actual point trying to be made, but it never came.
Yes, some things run only on specific hardware and without virtualization/emulation, you're not supposed to test those things outside of the hardware. Been a thing for decades, probably since the beginning of computing.
> How difficult can it be for Apple to make barebones virtual machines with just Safaris?
Almost nothing Apple does is seemingly decided by how difficult it is, for better or worse, but are strategic decisions. If you haven't caught up with that they're building a walled garden for themselves, I'm not sure what could convince that they are. I think this is extremely clear for most people. If you don't like it, don't play there, like the rest of us.
A lot of folks want to run tests off a GitHub action I.e. on a server somewhere.
Ideally you want your test stack to fit in a docker image. So this does suck for developers in the respect and you could imagine apple releasing a special docker image that just ran safari if they wanted to really make it easy to develop for thier platform.
However, I imagine someone will fill a server rack with cheap old macs and offer and safari mcp as a service…
No way, is Orion Browser available on other platforms as well now? Does it mean I can finally do tests for Safari (webkit) without owning an Apple product or paying for a vm? Incredible.
I have multiple Playwright webkits on both Windows and Linux. I have Epiphany on Linux (not 100% same webkit). I have subscriptions for testing on real hardware.
This is why it seems to me that Apple does not really care about web developers.
### THIS FILE IS AUTOMATICALLY CONFIGURED ###
# Changes to this file will not be preserved.
# This file will not be recreated if removed.
X-Repolib-Name: Microsoft Edge
Types: deb
URIs: https://packages.microsoft.com/repos/edge-stable
Suites: stable
Components: main
Architectures: amd64
Architectures: amd64
Signed-By: /usr/share/keyrings/microsoft-edge.gpg
> There are many ways to build for the web, both with and without AI. If AI is a part of your workflow, we think this tool will help make it even more productive. And if it isn’t, that’s OK too.
Crazy thing to say in 2026 where if you write code and not delegate every bit to an agent you're considered a noob by some people.
The opposite was considered two years ago a crazy thing to say. I'm glad this changed and people using ai don't have to hide in the closet anymore for doing so.
That’s the point I think. Remember the controversy when Github Copilot came out? Not because where it got its data from, but because people didn’t feel like they wrote code anymore, they just tabbed the autocompleted snippets and was finished with a task in much shorter time.
Which part makes it crazy? The fact that they felt the need to add this disclaimer to try to assuage the fanatical anti-AI contingent?
Like this is specifically a tool for AI-augmented development, and they had to add this "but also, thoughts and prayers for you non-AI people" is incredibly weird, but not in the way you seem to think it is.
I wonder if it supports Private Relay. Private Relay is great for getting around scraping blocks because they explicitly whitelist apple private Relay ips.
Should do. Private relay really would be a sweet alternative to residential scraping proxies, but I’d expect sites to put in additionally checks and captchas before too long.
https://developer.apple.com/icloud/prepare-your-network-for-... has a guide for web server operators, including a GeoIP CSV which could conceivably be used for whitelisting. More concerning is that they're plugging private access tokens there, which allows Apple to vouch that you're a human running their hardware.
Building something similar for Chrome and Firefox browsers: https://github.com/DO-SAY-GO/WebCLI - a CLI not MCP. Tho am considering MCP for distribution, even tho agents love the CLI and the proof demos speak for themselves.
The reason I did not include Safari was there wasn't enough parity between its Safaridriver surface and what Bidi/CDP give now. Safari is doing Bidi tho, iirc. So ...soon perhaps. ;) ;p xx ;p
Marketing iterations. Plus dang downweighted my posts after I got the biggest Show HN of last year, so I'm trying harder to get attn. HN maybe isn't the big launch - but it's kinda a legacy thing for me. Can't blame a guy for tryin
I have been using Chrome's official MCP devtools server since Nov 2025.
https://github.com/ChromeDevTools/chrome-devtools-mcp
Before that I used Chrome web drivers but MCP is faster and more capable.
I also instruct LLMs to test my pages on Firefox using its official MCP to make sure they work in Firefox too:
https://github.com/mozilla/firefox-devtools-mcp
Now I will add Safari to the compatibility tests. cool
Is there a difference between using these and using the playwright mcp with Chrome/Firefox config?
I can speak for Chrome's MCP which I have more experience.
devtools MCP will have access to more deep level fetures such as performance profiling, lighthouse and network requests in details.
For example, I had success using chrome devtools mcp to debug frontend performance issues. The LLM captured and analyzed some nice traces and was able to spot bottlenecks and unnecessary repaints and reflows.
I'd personally suggest Playwright-CLI: https://github.com/microsoft/playwright-cli
It works much faster for me than the MCP servers I tried.
Also, spel (https://github.com/Blockether/spel) for persistent browser sessions (through a daemon) and Chromium, Firefox, and WebKit engines.
All this felt heavy to me. Full browser, debug protocol, DOM dump on every read. MCP vs CLI is the smaller question, what sits underneath matters more. So I built a small Rust binary that drives the system webview directly and returns state tokens and deltas instead of the DOM. Loading the HN front page costs the agent about 50 tokens. It speaks both MCP and CLI, pick whichever your agent prefers.
https://github.com/frane/vibesurfer
But does Apple really care about web developers?
How do you test on Safari if you don’t have Apple devices?
How difficult can it be for Apple to make barebones virtual machines with just Safaris?
> How do you test on Safari if you don’t have Apple devices?
How do you test a Playstation game without a Playstation (dev kit)? How do you test some hardware firmware without having the hardware? How can you run a program without the hardware required to run the program, if no emulator/simulator is available?
I'm almost lost at words how these are questions, unless they're theoretical and some diatribe comes afterwards that has the actual point trying to be made, but it never came.
Yes, some things run only on specific hardware and without virtualization/emulation, you're not supposed to test those things outside of the hardware. Been a thing for decades, probably since the beginning of computing.
> How difficult can it be for Apple to make barebones virtual machines with just Safaris?
Almost nothing Apple does is seemingly decided by how difficult it is, for better or worse, but are strategic decisions. If you haven't caught up with that they're building a walled garden for themselves, I'm not sure what could convince that they are. I think this is extremely clear for most people. If you don't like it, don't play there, like the rest of us.
A lot of folks want to run tests off a GitHub action I.e. on a server somewhere. Ideally you want your test stack to fit in a docker image. So this does suck for developers in the respect and you could imagine apple releasing a special docker image that just ran safari if they wanted to really make it easy to develop for thier platform.
However, I imagine someone will fill a server rack with cheap old macs and offer and safari mcp as a service…
Even in the Chrome hegemony you don't want to be missing Edge and many others, so you test chromium.
Similarly, while not perfect you can test WebKit, and if you like, on Linux or Windows, for example:
https://orionbrowser.com/platforms/linux
Apple wouldn't be in the business of VMs with Safari, but if you're looking for MacOS VMs, turn to a CSP: https://aws.amazon.com/ec2/instance-types/mac/
Many have software testing orchestration pre-wired.
No way, is Orion Browser available on other platforms as well now? Does it mean I can finally do tests for Safari (webkit) without owning an Apple product or paying for a vm? Incredible.
I know of the solutions. I use a few of them.
I have multiple Playwright webkits on both Windows and Linux. I have Epiphany on Linux (not 100% same webkit). I have subscriptions for testing on real hardware.
This is why it seems to me that Apple does not really care about web developers.
Just like you would test IE on Linux or OS X.
I said IE, not Edge.
But why would you still test for IE in 2026?
Honest question. I’s < .5% market share and retired since 2023.
> There are many ways to build for the web, both with and without AI. If AI is a part of your workflow, we think this tool will help make it even more productive. And if it isn’t, that’s OK too.
Crazy thing to say in 2026 where if you write code and not delegate every bit to an agent you're considered a noob by some people.
The opposite was considered two years ago a crazy thing to say. I'm glad this changed and people using ai don't have to hide in the closet anymore for doing so.
When have people using AI to develop ever had to hide in any closet? It's the most public "new hotness" ever.
That’s the point I think. Remember the controversy when Github Copilot came out? Not because where it got its data from, but because people didn’t feel like they wrote code anymore, they just tabbed the autocompleted snippets and was finished with a task in much shorter time.
Which part makes it crazy? The fact that they felt the need to add this disclaimer to try to assuage the fanatical anti-AI contingent?
Like this is specifically a tool for AI-augmented development, and they had to add this "but also, thoughts and prayers for you non-AI people" is incredibly weird, but not in the way you seem to think it is.
should say "see how my website performs on safari"
I wonder if it supports Private Relay. Private Relay is great for getting around scraping blocks because they explicitly whitelist apple private Relay ips.
Should do. Private relay really would be a sweet alternative to residential scraping proxies, but I’d expect sites to put in additionally checks and captchas before too long.
Which sites explicitly whitelist Private Relay IPs?
https://developer.apple.com/icloud/prepare-your-network-for-... has a guide for web server operators, including a GeoIP CSV which could conceivably be used for whitelisting. More concerning is that they're plugging private access tokens there, which allows Apple to vouch that you're a human running their hardware.
so it's a crossover of dev tools and LLM? sounds sane enough i'd say
Does this support mobile simulator safari too
Building something similar for Chrome and Firefox browsers: https://github.com/DO-SAY-GO/WebCLI - a CLI not MCP. Tho am considering MCP for distribution, even tho agents love the CLI and the proof demos speak for themselves.
The reason I did not include Safari was there wasn't enough parity between its Safaridriver surface and what Bidi/CDP give now. Safari is doing Bidi tho, iirc. So ...soon perhaps. ;) ;p xx ;p
Not sure you want to hear this but there is 0% chance I will ever bring up a product with a vulgar name at work.
Not really sure why your project needs to be so… edgy?
Marketing iterations. Plus dang downweighted my posts after I got the biggest Show HN of last year, so I'm trying harder to get attn. HN maybe isn't the big launch - but it's kinda a legacy thing for me. Can't blame a guy for tryin
The actual site is: https://duetbrowser.com/