TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Hyperbrowser MCP Server – Connect AI agents to the web through browsers

63 点作者 shrisukhani大约 2 个月前
Hi HN! Excited to share our MCP Server at Hyperbrowser - something we’ve been working on for a few days. We think it’s a pretty neat way to connect LLMs and IDEs like Cursor &#x2F; Windsurf to the internet.<p>Our MCP server exposes seven tools for data collection and browsing:<p>1. `scrape_webpage` - Extract formatted (markdown, screenshot etc) content from any webpage<p>2. `crawl_webpages` - Navigate through multiple linked pages and extract LLM-friendly formatted content<p>3. `extract_structured_data` - Convert messy HTML into structured JSON<p>4. `search_with_bing` - Query the web and get results with Bing search<p>5. `browser_use_agent` - Fast, lightweight browser automation with the Browser Use agent<p>6. `openai_computer_use_agent` - General-purpose automation using OpenAI’s CUA model<p>7. `claude_computer_use_agent` - Complex browser tasks using Claude computer use<p>You can connect the server to Cursor, Windsurf, Claude desktop, and any other MCP clients with this command `npx -y hyperbrowser-mcp` and a Hyperbrowser API key. We&#x27;re running this on our cloud browser infrastructure that we&#x27;ve been developing for the past few months – it handles captchas, proxies, and stealth browsing automatically.<p>Some fun things you can do with it: (1) deep research with claude desktop, (2) summarizing the latest HN posts, (3) creating full applications from short gists in Cursor, (3) automating code review in cursor, (4) generating llms.txt for any website with windsurf, (5) ordering sushi from windsurf (admittedly, this is just for fun - probably not actually going to do this myself).<p>We&#x27;re building this server in the open and would love feedback from anyone building agents or working with web automation. If you find bugs or have feature requests, please let us know! One big issue with MCPs in general is that the installation UX sucks and auth credentials have to be hardcoded. We don’t have a solution to this right now but Anthropic seems to be working on something here so excited for that to come out. Love to hear any other complaints &#x2F; thoughts you have about the server itself, Hyperbrowser, or the installation experience.<p>You can check us out at <a href="https:&#x2F;&#x2F;hyperbrowser.ai">https:&#x2F;&#x2F;hyperbrowser.ai</a> or check out the source code at <a href="https:&#x2F;&#x2F;github.com&#x2F;hyperbrowserai&#x2F;mcp" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;hyperbrowserai&#x2F;mcp</a>

4 条评论

xena大约 2 个月前
Is there support for robots.txt so service operators can opt out of your mass scraping?
评论 #43443638 未加载
评论 #43441960 未加载
评论 #43442116 未加载
TheTaytay大约 2 个月前
This looks cool.<p>1) I looked at the pricing. Is search included in the price - (you just pay credits&#x2F;browser time?)<p>2) Can you tell me more about the source of your residential proxies? I am new to this space, so don’t know how people source these legitimately.<p>Thanks!
评论 #43441092 未加载
pizzafeelsright大约 2 个月前
Fantastic.<p>MCPs are showing promise.
评论 #43441170 未加载
评论 #43441100 未加载
dennisaxu大约 2 个月前
dope