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)
A server you run yourself between AI agents and your accounts; by default, writes wait for your yes.
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。
Authorization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 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
在终端中运行这条命令
claude mcp add --transport http recued 'https://{recued_host}/mcp' --header 'Authorization: Bearer {recued_key}'运行前请先填写空着的值。
地址中有只有你知道的 {…} 部分(例如你的账户),请复制后自行填写。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"recued": {
"url": "https://{recued_host}/mcp",
"headers": {
"Authorization": "Bearer {recued_key}"
}
}
}
}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。
地址中有只有你知道的 {…} 部分(例如你的账户),请复制后自行填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"recued": {
"type": "http",
"url": "https://{recued_host}/mcp",
"headers": {
"Authorization": "Bearer {recued_key}"
}
}
}
}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。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 必填 HTTP header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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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 recued.com 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
这个地址需要填入你自己的账户信息,所以我们无法替你检查
这个地址需要填入你自己的账户信息,所以我们无法替你检查
尚未检查;我们会在检查端点时读取工具列表
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。
你需要填写:Authorization
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(26.10.27)于9天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Intervals MCP
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.
Remote MCP server for intervals.icu run data and analysis
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。
Demo | Documentation | Marketplace
Give an AI agent the key to your email or CRM, and it can do anything that key allows. Recued is a self-hosted gateway between AI agents and your accounts, and the agent never gets the key. It gets only the tools you grant it. By default, anything that writes, sends, or deletes waits for your yes. So an agent can be useful without acting behind your back. Your mail, calendar, files, and CRM records stay on a machine you control.
It works two ways. An AI agent you already use gets in over MCP, through a contract that lists exactly what it may do. Or Recued does the job itself: you ask in its chat, or a recipe runs on a schedule or when something happens. Either way, every action passes the same gate.
Recued does not replace the AI you use. Claude, ChatGPT, Codex, or a local model still does the thinking. Recued is where that thinking meets your data and your accounts, on terms you set. That is the space it holds, between you and AI.
This repo holds the complete self-hosted server and the webclient. It also holds the workspace packages they are built from.
SKILL.md files. Recued cannot run them.One command. It fetches the signed binary for your platform. That is the program file, stamped so you know it is really from Recued. It checks it against the release key. It puts recued on your PATH, so you can run it from anywhere. And it sets it to start when you log in.
# Linux and macOS
curl -fsSL https://recued.com/install.sh | sh
# Windows — in PowerShell
irm https://recued.com/install.ps1 | iex
The installer starts the server too. So when it is done, the server is already running. To pair a browser, run recued pair. It prints a pairing code and a link to the webclient. Open the link and type in the code. If recued is not found in that terminal, open a new one.
Do not want it to start at login? Put RECUED_AUTOSTART=0 just before sh: curl -fsSL https://recued.com/install.sh | RECUED_AUTOSTART=0 sh. Put it before curl, and only curl sees it. In PowerShell, run $env:RECUED_AUTOSTART=0 on its own line first. Then start it yourself with recued serve. It prints the pairing code. The install location, the release channel, and the rest are in INSTALL.md.
A headless Linux box is one with no screen or desktop. There, starting at boot needs root, the admin account. Run the installer with sudo, and pair with sudo too. The installer prints the exact command. Here is why. Without a desktop keyring, there is only one way to seal the key file to the machine. That way reads a host key only root can read. A Linux desktop session installs a user unit and needs no root.
A pack is a JSON file. It says how to connect to any resource: a CLI, a SaaS, a REST API, or MCP. You can set permissions for each operation. By default, every write, admin, and destructive action needs your approval by hand. Ready-made packs are free at https://recued.com/packs. You can make your own with the built-in editor, or in JSON.
SKILL.md and recipesA skill tells a model how to approach something. The model decides each step as it runs. A recipe is the steps themselves. It is JSON, fixed before the run. The server runs it. It calls a model only where judgment is really needed.
They are not rivals. Recued offers recipes over MCP. So the skill that decides *this morning is worth looking at* can hand the work to a recipe. The only question is which half of a job belongs in which.
Every Monday morning: pull the past week's rising search terms from Google Trends. Then work out whether there is anything worth selling against them.
The hard step is the first one, and it is not a lookup. Trending searches name people, teams, and events: bmw championship payout, hurricanes weather. None of those is a product. A golf tournament means gloves and rangefinders. A storm means battery lanterns. And plenty of terms warrant nothing at all. Deciding that is the one part of this job a model has to do. The rest is fetching and arithmetic: what each keyword sells, what its clicks cost, and what is left.
We ran the same job three ways, on the same data with the same model. Tokens are the small pieces of text a model counts.
| the same job as | tokens | result |
|---|---|---|
| a recipe: 36 steps, 2 model calls | 13,385 | top 15 exact, in order |
| a skill that fetches to disk (we wrote this one) | 61,045 | top 15 exact, in order |
| a skill written blind, data through its context | 116,834 · 133,836 | no valid answer |
The blind skill is a good one, not a strawman. Why its runs gave no valid answer is in the write-up.
The best skill is not less correct. It reached the same fifteen products in the same order. But look at what it has become: a program with a natural-language wrapper. It needs its own secret keys, retries, and rate limits. It needs a place to keep the file. And it needs a way to run on Tuesday, when nobody opens a session. A recipe is that program, on a server that already has all of those.
The full write-up is in [`examples/`](./examples/README.md). It has the recipe itself. It has the skill it is measured against, written blind. It says what is real here and what is mocked. And it tells what happened when one sentence of our own prompt was wrong.
I built some real business apps to show what Recued can do:
只显示了开头部分;其余内容请在仓库中阅读