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)
Local MCP gateway for approved jobs, current agent permissions and durable retry inspection.
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": {
"continuity-gateway": {
"command": "npx",
"args": [
"-y",
"@ramex-labs/continuity-mcp-gateway",
"--config"
]
}
}
}在终端中运行这条命令
claude mcp add continuity-gateway -- npx -y @ramex-labs/continuity-mcp-gateway --config这个服务器需要在启动命令中填入值,请复制设置后自行填写。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"continuity-gateway": {
"command": "npx",
"args": [
"-y",
"@ramex-labs/continuity-mcp-gateway",
"--config"
]
}
}
}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。
这个服务器需要在启动命令中填入值,请复制设置后自行填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"continuity-gateway": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ramex-labs/continuity-mcp-gateway",
"--config"
]
}
}
}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9日
注册名称已通过 GitHub 账户 zerohourzulu 验证,该账户拥有此仓库
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(0.3.0-preview.11)于29天前进入注册中心。
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 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Bestax
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ 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.
Props, examples, CSS variables and Agent Skills for bestax-bulma React components (Bulma v1)
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。
Message package preview — 10 October 2026: Core11, remote6, gateway11 and evidence12 add the optional saved-record explanation command. See the current release guide. Existing API/policy/proof behavior stays unchanged; older npm archives remain available.
Source preview.13: MCP client/server/core updated to 2.2.0 for GHSA-6qxp-vccf-f47h. New MCP archives are source-prepared; npm and Registry still select the earlier published tuple.
Previous source preview.12.1: Plain-language messages, completed historical ZK experiments, and retained-receipt reader source. The installable packages now include the optional saved-output explanation command; use the exact tuple in the release guide.
Current developer preview: Exact versions and installation.
Follow an investigation: Follow one protected case through interruption, replacement, a signed completion, new evidence and a persistent challenge. Run the walkthrough.
Continue an existing case: Same case, longer history, preserved permissions and unfinished duties. Start with supported profiles, migration and recovery, or the protected evidence example.
Core 0.3 preview: Build a fresh case, connect approved MCP tools, or run the public tests. The original 0.2.2 evaluation releases remain available.
[Explore the interactive demo →](https://zerohourzulu.github.io/continuity/) · Start here · Developer guide · Security and limits
[Try your own choices in the playground →](https://continuity.ramex.com/playground/) No installation or account needed.
Developer preview · Apache 2.0. Release status.
A process supervisor can start Agent B. Continuity records which role B occupies, which powers it has, what happened before, and which unfinished duties survive the change. A replacement receives its explicitly granted powers; an unfinished duty does not silently grant more authority.
The original tutorial follows a security investigation interrupted by an agent replacement. The old request is refused, the investigation stays OPEN, and the successor’s review permission is checked independently.
| You want to… | Start here | What you will learn |
|---|---|---|
| Understand the idea without installing anything | The story and answer key | Why an unfinished duty and permission are separate. |
| Run and inspect a replacement | Tutorial, then operator commands | What was refused, who holds the duty and what B may do. |
| Evaluate or integrate the code | Core 0.3 quickstart | Create your own permissions, try a protected tool, then connect a framework or policy engine. |
Use Node 22.18+ (22.x), 24.x or 26.x on macOS or Linux. Prefer the latest patch of your chosen release. No global pnpm or Python is needed for this tutorial. Full quickstart, including archive extraction.
Get the public source; no GitHub account is needed:
git clone https://github.com/zerohourzulu/continuity.git
cd continuity
<!-- /quickstart -->
See the result first, without installing dependencies:
node examples/recorded.mjs
Expect ALLOW for reviewing the investigation and DENY for collecting another packet. This inspects a bundled recorded case; it does not execute a new action.
Generate your own evidence:
node tools/setup.mjs
node tutorial/start.mjs
<!-- /quickstart -->
Expect PASS — duty remains OPEN; B has no collection power, then VERIFIED. Setup downloads locked dependencies with scripts disabled. The tutorial then runs locally using synthetic data and public test keys. It prints your new case name and exact follow-up commands. Rerunning creates another case and preserves earlier evidence.
Change one permission:
node tutorial/start.mjs --deny-review
B still inherits the duty, but its review permission becomes DENY. Expected output and explanation · Setup checks and recovery.
Keep records locally, or choose a chain-backed deployment to make selected history publicly verifiable. Cryptographic commitments can let authorized reviewers check private records without publishing their contents. This tutorial runs locally; each deployment has its own privacy, availability and finality requirements.
| Your next step | Where to go |
|---|---|
| See the idea and recorded comparison | Interactive demo |
| Inspect your new run and optional recorded Linux evidence | Operator guide |
| Integrate an authority check | Developer guide · Executable reader example |
| Try optional native enforcement mechanics | Disposable Linux lab |
| Review source provenance and validation | Validation · Presentation checks · Provenance |
| Extend the presentation | Website maintenance |
Presentation maintainers can find the separate owner-private edition in website maintenance. The public walkthrough needs no account.
Read the short development history from Core 0.1 to the current reference implementation. Contributions and public RFCs are welcome; an RFC is useful for changes to protocol behavior or security boundaries.
Core 0.2.2 is local reference software. It is not a hostile-agent sandbox, production credential system or autonomous cyber defender. The website selects recorded results; the downloaded tutorial executes Core. Real integrations must mediate every consequential operation through a protected executor. Security boundaries.
The source, tutorial, tests, reader and website are included here and in the complete evaluation download. Earlier editions remain available as historical releases; use evaluation.6 for the commands above. Package overview · Presentation provenance.
Release status and licensing · Apache 2.0 license · Third-party notices
Try the standalone developer package: install the supplied JavaScript SDK tarball in a separate application, create one authorized synthetic packet, and inspect why refused requests create none. Includes TypeScript declarations and an offline consumer check. This is an evaluation interface around unchanged Core0.2.2.
The shared-package preview connects the cooperating remote tools and MCP evidence tool to one Core dependency. Try native LangChain tools and lost-reply recovery, or the MCP evidence tool.