[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-related-ko-myon-bioinformatics-mcp-toolcall-lab":3},{"items":4,"total":102,"page":103,"pageSize":104},[5,24,41,65,82],{"slug":6,"name":7,"categorySlug":8,"summary":9,"description":9,"categoryName":10,"sourceUrl":11,"homepageUrl":-1,"downloadUrl":12,"cliCommand":-1,"primaryLanguage":13,"license":14,"stars":15,"forks":16,"trendScore":17,"qualityScore":18,"supportedClients":19,"clients":20,"tags":21,"installCommand":-1,"configSnippet":-1,"useCases":22,"updatedAt":23},"browserbase-mcp","Browserbase MCP","browser-automation","Give agents controlled browser sessions for research, QA, screenshots, and web tasks.","Browser automation","https:\u002F\u002Fgithub.com\u002Fbrowserbase\u002Fmcp-server-browserbase","https:\u002F\u002Fgithub.com\u002Fbrowserbase\u002Fmcp-server-browserbase\u002Farchive\u002FHEAD.zip","Python","Apache-2.0",13290,410,96,89,[],[],[8,13,14],[],"2026-06-21T00:00:00",{"slug":25,"name":26,"categorySlug":8,"summary":27,"description":28,"categoryName":10,"sourceUrl":29,"homepageUrl":-1,"downloadUrl":30,"cliCommand":-1,"primaryLanguage":-1,"license":31,"stars":32,"forks":33,"trendScore":34,"qualityScore":35,"supportedClients":36,"clients":37,"tags":38,"installCommand":-1,"configSnippet":-1,"useCases":39,"updatedAt":40},"seleniumbase-seleniumbase","seleniumbase\u002Fseleniumbase","Browser automation, web scraping, and testing. CDP Mode provides a Stealthy Chromium instance that bypasses bot-detection systems. Includes an MCP server.","All-in-one Browser Automation Framework: Web Crawling \u002F Testing \u002F Scraping \u002F Stealth\n\n🚀 Start | 🏰 Features | 🎛️ Options | 📚 Examples | 💻 Scripts | 🗾 Locale 📗 API | 📘 Stealth API | 🔠 DesignPatterns | 🔴 Recorder | 📊 Dashboard 🎖️ GUI | 📰 TestPage | 👤 UC Mode | 🐙 CDP Mode | 📶 Charts | 🖥️ Farm 👁️ How | 🚝 Migration | 🎭 Stealthy Playwright | 🛂 MasterQA | 🚎 Tours 🤖 MCP | 🟨 JS Mgr | 🌏 Translator | 🎞️ Presenter | 🖼️ Visual | 🗂️ CPlans\n\n🐙 CDP Mode bypasses bot-detection with Chromium-based browsers. 🎭 Stealthy Playwright Mode extends CDP Mode's stealth to Playwright. pip install seleniumbase for the main framework. (Or use uv add ) pip install playwright for the optional integration. (Or use uv add )\n\n🤖 For the seleniumbase-mcp MCP server, see the MCP ReadMe .\n\n📝 Here's a Python example that uses Pure CDP Mode ( sb_cdp ): (It navigates to Browserscan where it bypasses bot-detection.)\n\n(All BrowserScan bot-detection tests passed successfully.","https:\u002F\u002Fgithub.com\u002Fseleniumbase\u002Fseleniumbase","https:\u002F\u002Fgithub.com\u002Fseleniumbase\u002Fseleniumbase\u002Farchive\u002FHEAD.zip","MIT",13068,1596,90,68,[],[],[8,31],[],"2026-09-21T02:31:22.416533",{"slug":42,"name":43,"categorySlug":8,"summary":44,"description":45,"categoryName":10,"sourceUrl":46,"homepageUrl":-1,"downloadUrl":47,"cliCommand":-1,"primaryLanguage":-1,"license":31,"stars":48,"forks":49,"trendScore":50,"qualityScore":34,"supportedClients":51,"clients":54,"tags":62,"installCommand":-1,"configSnippet":-1,"useCases":63,"updatedAt":64},"dsphper-lanhu-mcp","dsphper\u002Flanhu-mcp","⚡ 需求分析效率提升 200%！全球首个为 AI 编程时代设计的团队协作 MCP 服务器，自动分析需求自动编写前后端代码，下载切图","一个功能强大的 Model Context Protocol (MCP) 服务器，专为 AI 编程时代设计，完美支持蓝湖（Lanhu）设计协作平台。\n\n🔥 ： - 📋 ：自动提取 Axure 原型，三种分析模式（开发\u002F测试\u002F探索），需求分析准确率>95% - 💬 ：打破 AI IDE 孤岛，让所有 AI 助手共享知识库和上下文 - 🎨 ：自动下载设计稿，智能提取切图，语义化命名；设计图分析可获取尺寸\u002F间距\u002F颜色\u002F字体等精确参数，并得到转换后的 HTML+CSS 代码参考 - ⚡ ：基于版本号的智能缓存，增量更新，并发处理\n\n🎯 ： - ✅ Cursor + 蓝湖：让 Cursor AI 直接读取蓝湖需求文档和设计稿 - ✅ Windsurf + 蓝湖：Windsurf Cascade AI 直接读取蓝湖需求文档和设计稿 - ✅ Claude Code + 蓝湖：Claude AI 直接读取蓝湖需求文档和设计稿 - ✅ OpenClaw + 蓝湖：OpenClaw 原生支持读取蓝湖需求文档和设计稿 - ✅ ClawBot + 蓝湖：ClawBot 智能助手深度集成蓝湖协作 - ✅ Trae + 蓝湖：Trae AI 直接读取蓝湖需求文档和设计稿 - ✅ 通义灵码 + 蓝湖：通义灵码 AI 直接读取蓝湖需求文档和设计稿 - ✅ Cline + 蓝湖：Cline AI 直接读取蓝湖需求文档和设计稿 - ✅ 任何支持 MCP 协议的 AI 开发工具\n\n🎯 ： - ❌ ：每个开发者的 AI 独立工作，重复分析需求，无法共享经验 - ✅ ：所有 AI 连接同一知识中枢，需求分析一次、全员复用，踩坑经验永久保存\n\n- ：自动下载和解析 Axure 原型的所有页面、资源和交互 - ： - 🔧 ：详细字段规则、业务逻辑、全局流程图 - 🧪 ：测试场景、用例、边界值、校验规则 - 🚀 ：核心功能概览、模块依赖、评审要点 - ：全局扫描 → 分组分析 → 反向验证 → 生成交付物 - ：基于 TODO 驱动的系统化分析流程\n\n- ：批量下载和展示 UI 设计图 - ：分析时不仅返回设计图预览，还可获取**（组件尺寸、间距、颜色值、字体大小等），并自动将设计 Schema 转为 ，与蓝湖原生导出效果一致，便于 AI 参考实现 - ：自动识别和导出设计切图、图标资源 -...","https:\u002F\u002Fgithub.com\u002Fdsphper\u002Flanhu-mcp","https:\u002F\u002Fgithub.com\u002Fdsphper\u002Flanhu-mcp\u002Farchive\u002FHEAD.zip",2470,272,78,[52,53],"cursor","cline",[55,59],{"slug":52,"name":56,"summary":57,"count":58},"Cursor","개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.",0,{"slug":53,"name":60,"summary":61,"count":58},"Cline","MCP 통합이 많은 에이전트형 코딩 워크플로 클라이언트.",[8,31],[],"2026-08-30T08:28:01.835032",{"slug":66,"name":67,"categorySlug":8,"summary":68,"description":69,"categoryName":10,"sourceUrl":70,"homepageUrl":-1,"downloadUrl":71,"cliCommand":-1,"primaryLanguage":-1,"license":72,"stars":73,"forks":74,"trendScore":75,"qualityScore":76,"supportedClients":77,"clients":78,"tags":79,"installCommand":-1,"configSnippet":-1,"useCases":80,"updatedAt":81},"isair-jarvis","isair\u002Fjarvis","A 100% private AI voice assistant that lives on your computer (works offline). Talk naturally as if Jarvis is a third person in the room, and get conversational responses.","A private, local-first voice assistant that lives on your computer. Talk naturally, as if Jarvis were a third person in the room.\n\nJarvis is built to be part of the conversation. Talk through an idea, discuss plans with a friend, then ask “Jarvis, what do you think?” While listening, it keeps a short, temporary rolling transcript of nearby speech so it can join an ongoing conversation using what was just discussed.\n\nAddress Jarvis by name anywhere in a sentence and follow up naturally. Speech recognition, language models and speech synthesis run on hardware you control.\n\nYour conversation and all data stays solely on your computer. Sensitive information is redacted before it reaches model context or the saved diary, even though both are local, to ensure the security of your private information. Web search, weather and connected tools use the network but send only what is necessary when you ask for those capabilities.\n\nA voice, a face, and a place in the conversation.","https:\u002F\u002Fgithub.com\u002Fisair\u002Fjarvis","https:\u002F\u002Fgithub.com\u002Fisair\u002Fjarvis\u002Farchive\u002FHEAD.zip","NOASSERTION",2068,407,76,61,[],[],[8,72],[],"2026-10-13T01:54:02.699168",{"slug":83,"name":84,"categorySlug":8,"summary":85,"description":86,"categoryName":10,"sourceUrl":87,"homepageUrl":-1,"downloadUrl":88,"cliCommand":-1,"primaryLanguage":-1,"license":89,"stars":90,"forks":91,"trendScore":75,"qualityScore":92,"supportedClients":93,"clients":95,"tags":99,"installCommand":-1,"configSnippet":-1,"useCases":100,"updatedAt":101},"vmoranv-jshookmcp","vmoranv\u002Fjshookmcp","A search-first, profile-aware reverse-engineering workspace for AI agents — 735 tools across 36 domains in one MCP server.","What's different · Capabilities · Use cases · Highlights · Transport · Registry · Architecture · Build\n\nDocumentation · Getting Started · Configuration · Tool Reference\n\nSponsored by Swiftproxy — Premium Residential Proxies for Web Automation · 10% off code: PROXY90\n\nMost MCP servers for JS analysis expose a handful of hand-rolled tools or wrap a single browser engine. jshook is closer to an — 36 self-discovered domains, a search-first meta-tool that keeps token cost under control, and runtime recovery that survives broken pages and dropped sessions:\n\n- The search profile loads about 3K tokens of tool metadata; the full profile exposes all 735 tools at around 109K tokens (measured 2026-10-10 — this figure scales with the tool count, so re-measure it when the catalog grows). Agents move between them as the task grows — search → workflow → full — instead of drowning in schemas from the first turn.","https:\u002F\u002Fgithub.com\u002Fvmoranv\u002Fjshookmcp","https:\u002F\u002Fgithub.com\u002Fvmoranv\u002Fjshookmcp\u002Farchive\u002FHEAD.zip","AGPL-3.0",2045,460,88,[94],"claude-desktop",[96],{"slug":94,"name":97,"summary":98,"count":58},"Claude Desktop","로컬 MCP 설정을 지원하는 데스크톱 클라이언트.",[8,89],[],"2026-10-12T02:49:05.135348",137,1,5]