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

Here's a breakdown of the key themes emerging from the Hacker News discussion about Browser MCP, along with supporting quotes:

Several users discussed the place of "MCP" (interface layer to AI) in the broader landscape of automation.

MCP as distinct from RPA: "No, since MCP is just an interface layer it is to AI what REST API is to DPA and COM/App DLLs are to RPA. APA (Agentic Process Automation) is the new RPA, and this is definitely one example of it." (ajcp)

A central theme is the benefit of Browser MCP related to reusing the user's existing browser context and avoiding bot detection.

Sharing Browser Context: "Ooo, i like that. one of the most annoying points has been 'not sharing' the browser context. i'll def check it out" (buttofthejoke)
Avoiding Bot Detection: "Avoids bot detection and CAPTCHAs by using your real browser fingerprint." (hannofcart, quoting the project's page)
Elaboration on Browser MCP uniqueness: "Currently Browser MCP is largely an adaptation of the Playwright MCP server to use with your actual browser rather than creating a new one each time. This allows you to reuse your existing Chrome profile so that you don't need to log in to each service all over again and avoids bot detection which often triggers when using the fresh browser instances created by Playwright." (namukang)

The developer (namukang) and other users emphasized the convenience and ease of use of the extension-based approach.

Convenience over remote debugging: "An extension is more user-friendly! I leave Chrome open basically 24/7 and having to create a new Chrome instance via the command line just to use Browser MCP just felt like too high of a barrier." (namukang)
Improved user experience compared to existing tools: "Well done, just tested on Claude Desktop and it worked smoothly and a lot less clunky than playwright. This is the right direction to go in." (neilellis)

A significant point of discussion revolved around the privacy implications of sending browsing data to AI models and potential risks.

Concerns about data exposure: "I think this is bullshit. Isn't the dom or whatever sent to the model api?" (johnpaulkiser)
Clarification of privacy in local vs. remote automation: "Of course, you're sending data to the AI model, but the 'private' aspect is contrasting automating using a local browser vs. automating using a remote browser...With Browser MCP, since you're automating locally, your sensitive data and browser activity (apart from the results of MCP tool calls that's sent to the AI model) stay on your device." (namukang)
Emphasis on transparency and user awareness: "I think we need to be very careful & intentional about the language we use with these kinds of tools, especially now that the MCP floodgates have been opened. You aren't just exposing the users browsing data to which ever model they are using, you are also exposing it any tools they may be allowing as well...I would explicitly tell them that potentially 'all' of their browsing data is going to be exposed to their LLM client and they need to use this at their own risk." (johnpaulkiser)

Users suggested potential improvements and expansions for Browser MCP.

CAPTCHA handling improvements: "I don't know if you've done it already, but it would be great to pause automation when you detect a captcha on the page and then notify the user that the automation needs attention. Playwright keeps trying to plough through captchas." (neilellis)
Firefox support limitations: "Any plans to make a Firefox version?...Browser MCP uses the Chrome DevTools Protocol to automate the browser so it currently only works for Chromium-based browsers...Unfortunately, Firefox doesn't expose anything like the Chrome DevTool Protocol to browser extensions AFAIK (someone please correct me if I'm mistaken!), so I don't think I can support it even if I tried." (Fernicia, namukang)
Integration with other applications: "I wonder if it's possible to add such plugins to election apps (e.g.: Slack). It would be such a nice experience if I could just connect my AI of choice to a local app." (BrandiATMuhkuh)

Some users expressed concerns about the increasing use of bots and the potential need for stricter measures like CAPTCHAs.

Worry about increased bot traffic: "Good, just what we needed. More bots browsing the internet. Somedays I think I am not 100% against of every website having a captcha..." (101008)

Questions arose about the specific implementation of the demo, particularly regarding how the system obtains specific data.

Understanding data sources in the Task Automation demo: "In the Task Automation demo, how does it know all of the attributes of the motorcycle he is trying to sell? Is it relying on the underlying LLM's embedded knowledge? But then how would it know the price and mileage? Is there some underlying document not referenced in the demo? Because that information is not in the prompt." (DebtDeflation)

One user questioned the novelty of the project, pointing to existing solutions for browser automation using LLMs.

Criticism that the idea has been done before: "What I don't like about LLMs is that people keep re-inventing the wheel over and over. For example, we've been able to control browsers using GPT for about 2 years now..." (behnamoh)

Similar Topics