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)
Give your AI agent the ability to respond with live, interactive apps that evolve.
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。
SAC_API_KEY, SAC_API_BASE, SAC_MODEL, SAC_SEARCH_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"sac": {
"command": "uvx",
"args": [
"sac-sdk"
],
"env": {
"SAC_API_KEY": "your-value",
"SAC_API_BASE": "your-value",
"SAC_MODEL": "your-value",
"SAC_SEARCH_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add sac --env SAC_API_KEY=your-value --env SAC_API_BASE=your-value --env SAC_MODEL=your-value --env SAC_SEARCH_API_KEY=your-value -- uvx sac-sdk运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"sac": {
"command": "uvx",
"args": [
"sac-sdk"
],
"env": {
"SAC_API_KEY": "your-value",
"SAC_API_BASE": "your-value",
"SAC_MODEL": "your-value",
"SAC_SEARCH_API_KEY": "your-value"
}
}
}
}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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"sac": {
"type": "stdio",
"command": "uvx",
"args": [
"sac-sdk"
],
"env": {
"SAC_API_KEY": "your-value",
"SAC_API_BASE": "your-value",
"SAC_MODEL": "your-value",
"SAC_SEARCH_API_KEY": "your-value"
}
}
}
}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。
SAC_API_BASE envSAC_MODEL env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
发布者(dynsoft.ai)不是仓库所有者(Software-As-Content);可能是其他人代为上架的
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 0 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。
你需要填写:SAC_API_KEY, SAC_SEARCH_API_KEY
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(0.1.2)于6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 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, yontu
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.
Türkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup.
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。
AI agents can reason, code, and call APIs — but when they need to communicate back to you, all they have is text. SaC (Software as Content) is the missing interaction layer: your agent responds with a live, persistent, interactive app that evolves as the conversation continues. Not a screenshot, not a markdown wall — a real UI you click, explore, and shape together with your agent.
pip install sac-sdk
sac serve
First time? It'll ask for your API key and save it. Then open http://localhost:18420, type *"3-day Tokyo trip planner with budget"*, and watch a live React app stream in. Click buttons. Ask it to evolve. This is SaC running a built-in agent loop — no external agent needed.
SaC plugs into the agent you already use — through MCP, Skill, or code.
pip install sac-sdk
sac setup claude-code # registers SaC as an MCP server
Restart Claude Code. Then try:
*"Help me understand this codebase using a visualized and interactive app using SaC MCP."*
Setup details →
pip install sac-sdk
sac setup codex # installs the SaC skill sac serve # keep running in a terminal
Setup details →
pip install sac-sdk
sac setup openclaw # installs the SaC skill sac serve # keep running in a terminal
Setup details →
from sac import SaC
sac = SaC() conv = sac.conversation() app = await conv.generate("3-day Tokyo itinerary") print(app.url) # user opens this
Your agent ──▶ SaC ──▶ User sees a live app at a URL
◀── User clicks a button / types a message Your agent ──▶ SaC ──▶ Same URL, app evolves in place ◀── ...
One URL, one conversation. The agent doesn't generate a new page every turn — it evolves the existing app. Users keep their context; the agent keeps its state.
Two channels, one loop: every response is either a UI update (the app evolves) or a chat reply (a text bubble). Users can click buttons in the app OR type in the chat — both go back to the agent through the same callback.
SaC is for tasks where exploration and interaction matter more than a final answer.
Good fit: trip planning, data analysis dashboards, comparison shopping, project planning, research, financial reviews, decision aids, internal tools
Not the right tool for: simple Q&A, one-shot automations ("set an alarm"), conversations that are purely text
Every layer is pluggable:
from sac import SaC, FileStore
sac = SaC( llm=YourLLMProvider(...), # any class implementing LLMProvider search=YourSearchProvider(...), # any class implementing SearchProvider store=FileStore(".sac"), )
Prompts live in src/sac/runtime/prompts/ and the default design system is in src/sac/renderer/design-systems/default/.
src/sac/
├── sac.py / conversation.py Entry + Conversation primitive ├── runtime/ Generate + Evolve pipeline, prompts, providers ├── server/ │ ├── http/ FastAPI + SSE streaming + viewer │ └── mcp/ MCP stdio server (Claude Code integration) └── renderer/ iframe sandbox + design system
Full architecture →
v0.1.2 — alpha. The core protocol (generate → evolve → callback loop) is stable and runs in production at sac.dynsoft.ai. The SDK surface is being polished toward v1.0.
Issues and PRs welcome. Highest-leverage contributions right now:
src/sac/runtime/prompts/src/sac/renderer/design-systems/For local dev: pip install -e .
Apache-2.0