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)
The decision layer between an idea and a digital product that works.
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 …”。
适用于网页版、桌面版和手机版 Claude:
https://pabs.co.nz/api/mcp/{token}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。
在终端中运行这条命令
claude mcp add --transport http pabs 'https://pabs.co.nz/api/mcp/{token}'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": {
"pabs": {
"url": "https://pabs.co.nz/api/mcp/{token}"
}
}
}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": {
"pabs": {
"type": "http",
"url": "https://pabs.co.nz/api/mcp/{token}"
}
}
}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。
ChatGPT 只能连接互联网上的服务器:
https://pabs.co.nz/api/mcp/{token}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。
菜单名称可能因套餐和版本不同而略有差异。
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。
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10日
注册名称已通过 GitHub 账户 pdunovits 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
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。
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(1.0.0)于5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。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, Google Jobs
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.
Google Jobs listings (title, company, salary, description) + AI-training job boards.
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。
Give your AI coding tools live access to your product strategy.
PABS is a product strategy platform that turns a brief into a full strategy — hypotheses, competitor analysis, PRD, and a living pulse of your venture's health. The MCP server exposes that strategy to any MCP-compatible AI tool so it can build with context, not guesses.
When your AI builder knows the target audience, design hypotheses, and current strategic verdict, it makes better decisions. When it spots a gap between what was planned and what was built, it can report it back — and PABS queues it for your review.
Transport: Streamable HTTP (MCP 2025 spec) Server URL: https://pabs.co.nz/api/mcp/{your-token} Authentication: Bearer token (one per plan, generated in the PABS app)
Add to claude_desktop_config.json:
{
"mcpServers": { "pabs": { "type": "streamable-http", "url": "https://pabs.co.nz/api/mcp/YOUR_TOKEN" } } }
{
"mcpServers": { "pabs": { "type": "streamable-http", "url": "https://pabs.co.nz/api/mcp/YOUR_TOKEN" } } }
Add to .cursor/mcp.json in your project (or global settings):
{
"mcpServers": { "pabs": { "type": "streamable-http", "url": "https://pabs.co.nz/api/mcp/YOUR_TOKEN" } } }
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": { "pabs": { "serverUrl": "https://pabs.co.nz/api/mcp/YOUR_TOKEN" } } }
PABS - My App)https://pabs.co.nz/api/mcp/YOUR_TOKENThe server speaks the MCP 2025 Streamable HTTP transport. Send POST requests to the server URL with a Bearer token in the Authorization header, or embed the token directly in the URL path (as shown above).
| Tool | What it returns |
|---|---|
get_full_context | Everything in one call: brief, strategy, competitor analysis, documents, decisions, hypotheses, action plan, latest pulse, recent learnings. Recommended starting point. |
get_brief | Problem statement, target audience, goals, constraints, timeline |
get_product_strategy | Design hypotheses, customer goals, pain points, design vision, success metrics, experience principles |
get_competitor_analysis | Market intelligence, competitive positioning, opportunity analysis |
get_prd | Product Requirements Document generated for AI code builders |
get_documents | All generated documents: PRD, Statement of Work, Venture Brief |
get_decisions | Key assumptions, information gaps with priority/impact, recommended next steps |
get_hypotheses | Design hypotheses with target audience and success indicators |
get_action_plan | Staged activities with tools, durations, and deliverables |
get_pulse | Current strategic Pulse: verdict, recommended next move, activation level |
get_learnings | All captured learnings — evaluated and decided — with the full decision history |
get_pending_learnings | Learnings PABS has evaluated but that need a human decision |
get_pulse_schedule | Current Pulse cadence: day, time, timezone, frequency, next run |
| Tool | What it does |
|---|---|
ask_pabs_agent | Ask a strategic question. Returns alignment score, recommendations, and considerations. Automatically captures observations or implementation drift. |
report_learning | Push a real-world observation into the strategy feedback loop. PABS evaluates its impact and queues it for the founder to review. |
decide_learning | Approve, reject, or modify a pending learning inline — without opening PABS. |
trigger_pulse | Queue a fresh strategic Pulse after a significant build session or analytics review. |
| Tool | What it does |
|---|---|
schedule_pulse | Set the agentic Pulse cadence (frequency, day, hour, timezone). |
PABS is designed for a two-way relationship between AI builders and the strategy layer.
Outbound (strategy to builder): The builder calls get_full_context at the start of a session to load the current strategy, hypotheses, target audience, and decisions. It builds with that context.
Inbound (builder to strategy): As the builder works, it can call ask_pabs_agent to check whether a proposed feature aligns. If it observes something real — a drop-off, a pattern, a change in scope — it calls report_learning. PABS evaluates the learning against the strategy, proposes an adaptation, and notifies the founder.
Human in the loop: Strategy only updates after the founder reviews and approves a learning. get_pending_learnings and decide_learning let that review happen inline, inside the builder session.
Each plan has a unique token. Tokens do not expire by default. You can revoke and regenerate a token at any time from the PABS Connect tab.
The server URL with the token embedded (/api/mcp/{token}) is the recommended format — it lets AI clients distinguish between multiple plans as separate servers.
Alternatively, pass the token in the Authorization header as Bearer {token}, or in the X-PABS-Token header.
This repository documents the hosted PABS MCP server. The server is proprietary and operated by PABS. Client configuration examples in examples/ are released under MIT.