Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Record your screen and export studio-styled demo videos on macOS, driven by your AI assistant.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
链接指向作者自己的文件;我们不托管也不重新打包它。打开文件后,Claude Desktop 会进行安装。
在终端中运行这条命令
浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 screenify.studio 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(2.2.1)于3个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 MCPB。
同一分类中有:Spec Driven Development, Remote Desktop Commander, HotCodePush
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Manage over-the-air (OTA) updates for React Native, Expo, Capacitor and Cordova apps.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
**Every other screen-related MCP server lets an AI *look at* your screen. This one lets it *make a video*.**
Ask Claude, Claude Code or Cursor for a demo and get back a finished file — recorded, styled and exported. No terminal, no flags, no editor.
"Record a 12-second demo of my landing page and put it on a café desk mockup."
Everything runs locally on your Mac. Nothing is uploaded.
https://github.com/user-attachments/assets/8c753dcb-0e53-4c00-acd6-0cd934b19415
Asked in a chat window; recorded, styled and exported by Screenify. No editor was opened.
Connect it to an AI assistant and ask for the finished video instead of driving the editor yourself:
Everything runs locally on your Mac. Nothing is uploaded.
Requires [Screenify Studio](https://www.screenify.studio/download) 2.2.0 or newer. The bundle carries no binary — it launches the CLI that ships inside the app.
This repository is also a Claude plugin. It bundles the MCP server with a skill that teaches Claude which Screenify flow to use for a request. In Claude Code:
claude --plugin-dir /path/to/screenify-mcp
The plugin's server runs locally, so it works in Claude Code and in Cowork sessions on your Mac. In a regular Claude chat, use the one-click bundle below instead.
What the plugin runs. scripts/screenify-mcp.sh looks for the screenify command that ships inside the Screenify Studio app (/Applications/Screenify Studio.app, or the copy the app installs at ~/.screenify/bin) and starts it as an MCP server over stdio. It downloads and installs nothing. If the app is missing, it returns an error that tells you where to get it.
Download screenify.mcpb and open it. Claude Desktop installs the connector.
Open Screenify Studio → Settings → AI Assistants → Connect AI assistants. It registers the server with every AI client it finds on your Mac. Or from a terminal:
screenify mcp install
Screenify is listed in the official MCP registry as studio.screenify/screenify, so clients that read the registry can find and install it without any of the steps above.
Full policy: [www.screenify.studio/privacy](https://www.screenify.studio/privacy)
In short, for this MCP server specifically:
Issues with the MCP server or the app: support@screenify.studio
This repository — the Claude plugin (a manifest, a launcher script and a skill), the MCP bundle (screenify.mcpb: a manifest, a launcher script and an icon) and its documentation — is MIT licensed.
Screenify Studio itself is proprietary software and is not covered by that license. The app provides the MCP server, the recording pipeline and the export engine; this repo only ships the small bundle that launches it.