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)
VantaGate MCP Server & OpenAPI integration - Human-in-the-Loop for AI Agents
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。
VANTA_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": {
"vantagate": {
"command": "npx",
"args": [
"-y",
"@vantagate/mcp-server"
],
"env": {
"VANTA_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add vantagate --env VANTA_API_KEY=your-value -- npx -y @vantagate/mcp-server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": {
"vantagate": {
"command": "npx",
"args": [
"-y",
"@vantagate/mcp-server"
],
"env": {
"VANTA_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": {
"vantagate": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vantagate/mcp-server"
],
"env": {
"VANTA_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。
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 GitHub 账户 Aderix 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。
你需要填写:VANTA_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(1.0.2)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 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Zoo 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.
An MCP server that provides access to the Zoo API for various CAD operations and tools.
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。
Human-in-the-Loop authorization for AI Agents. VantaGate intercepts high-risk actions, routes them to a human approver via Slack or Email, and returns a cryptographically-signed decision - so your agent resumes or halts with a full audit trail.
AI agents are increasingly capable of executing consequential real-world actions: sending emails to thousands of users, deleting database records, moving money, deploying to production. VantaGate is the trust layer that ensures humans remain in control.
Agent hits risky action
↓ POST /v1/checkpoint ──→ Human receives Slack/Email notification ↓ ↓ id and status Human reviews payload & decides ↓ ↓ Poll GET /v1/checkpoint/{id} ←── Decision recorded + payload purged ↓ APPROVED → Resume workflow REJECTED → Halt + report reason
GET /checkpoint/{id} never returns the original payloadThis package ships two integration artifacts for connecting any AI agent to VantaGate:
| Artifact | File | Best for |
|---|---|---|
| OpenAPI 3.0 Spec | vanta-gate-openapi.json | No-code tools, OpenAI GPTs, Alice, n8n, Zapier |
| MCP Server | src/index.ts / dist/index.js | Claude Desktop, Cursor, Cline, any MCP-compatible agent |
The fastest path. No manual setup required.
Step 1: Get your API key from https://vanta-gate.com/dashboard/projects
Step 2: Add VantaGate to your Claude Desktop config.
Open your claude_desktop_config.json:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": { "vantagate": { "command": "npx", "args": ["-y", "@vantagate/mcp-server"], "env": { "VANTA_API_KEY": "YOUR_API_KEY_HERE" } } } }
Step 3: Restart Claude Desktop. The tools create_vantagate_checkpoint and check_vantagate_status will appear in Claude's tool list.
Step 4: Ask Claude to do something that requires approval:
*"Delete all records from the staging database where created_at < 2024-01-01"*
Claude will automatically pause, create a checkpoint, and tell you to check your email or Slack for the approval notification.
Import vanta-gate-openapi.json directly into your tool of choice.
API Key → Header: X-API-KEYThe GPT will now pause before high-risk tool calls and ask for human approval.
vanta-gate-openapi.jsonX-API-KEY to your VantaGate API key in the credential storecreate_vantagate_checkpoint to your agent's "before high-risk action" triggerX-API-KEY header in the credential configurationfrom langchain.tools import OpenAPITool
vanta_tool = OpenAPITool.from_openapi_spec( spec_path="./vanta-gate-openapi.json", headers={"X-API-KEY": os.environ["VANTA_API_KEY"]} ) agent = initialize_agent([vanta_tool], llm, agent=AgentType.OPENAI_FUNCTIONS)
create_vantagate_checkpointPauses the agent workflow and routes a human approval request.
When Claude uses it: Before any high-risk action - financial operations, data deletion, production deployments, bulk communications.
| Parameter | Type | Required | Description |
|---|---|---|---|
title | string | ✅ | Short title shown to approver. Max 200 chars. |
payload | object | ✅ | Full JSON context for the decision. Encrypted + purged after decision. |
description | string | ❌ | Additional context below the title. Max 1000 chars. |
options | string[] | ❌ | Decision options. First = approve action. Default: ["Approve", "Reject"]. Min 2, max 5. |
timeout | string | ❌ | Auto-expire duration: 30m, 4h, 2d. Default: 24h. |
notify_email | string | ❌ | Email address for magic-link notification. |
slack_webhook_url | string | ❌ | Slack webhook URL (Pro/Scale plans). From Dashboard → Add to Slack. |
callback_url | string | ❌ | Your HTTPS endpoint for signed decision webhook. |
Returns: checkpoint_id and step-by-step instructions for the agent.
check_vantagate_statusPolls the decision status of a pending checkpoint.
| Parameter | Type | Required | Description |
|---|---|---|---|
checkpoint_id | string | ✅ | The ID from create_vantagate_checkpoint. |
Returns: status (PENDING / APPROVED / REJECTED / RESOLVED / EXPIRED), selected_option, reject_reason, and the full audit trail.
Base URL: https://api.vanta-gate.com/v1 Authentication: X-API-KEY header
| Method | Endpoint | Description |
|---|---|---|
POST | /checkpoint | Create a checkpoint - pauses agent |
GET | /checkpoint/{id} | Poll for human decision |
GET | /checkpoint/secure/{token} | Decision UI (internal - magic link) |
POST | /checkpoint/secure/{token}/decide | Submit decision (internal - decision UI) |
PENDING → APPROVED (human chose first/positive option)
→ REJECTED (human rejected with optional reason) → RESOLVED (human chose non-primary option) → EXPIRED (timeout elapsed, no decision)
| HTTP | Code | Description |
|---|---|---|
| 400 | Invalid_Webhook_URL | slack_webhook_url must start with https://hooks.slack.com/ |
| 400 | Invalid_Callback_URL | callback_url is malformed or points to private IP |
| 400 | Invalid_Decision | Decision value not in checkpoint's options array |
| 400 | Validation_Error | Request body field validation failure |
| 401 | Unauthorized | Missing, invalid, or rotated API key |
| 402 | Upgrade_Required | Feature requires Pro or Scale plan |
| 403 | Forbidden | API key doesn't match the checkpoint's project |
| 404 | Not_Found | Checkpoint ID or token does not exist |
| 409 | Already_Decided | Decision already recorded for this checkpoint |
| 410 | Checkpoint_Expired | Timeout window has passed |
| 429 | Rate_Limited | Too many requests - back off and retry |
All errors follow the envelope:
{
"statusCode": 400, "error": "Machine_Readable_Code", "message": "Human-readable description." }
| Feature | Free | Pro ($49/mo) | Scale ($199/mo) |
|---|---|---|---|
| Checkpoints/month | 50 | 2,500 | 25,000 |
| Email notifications | ✅ | ✅ | ✅ |
| Slack notifications | ❌ | ✅ | ✅ |
| Webhook callbacks | ✅ | ✅ | ✅ |
| Max timeout | 24h | 7 days | 30 days |
| Log retention | 7 days | 90 days | 365 days |
Timeout values are silently clamped to your plan's maximum. A Free plan request with
timeout: "7d"will be capped to24h.
When a human decides, VantaGate sends a signed HTTPS POST to your callback_url (up to 5 retry attempts with exponential back-off).
Request headers:
Content-Type: application/json
X-Vanta-Signature: sha256= User-Agent: VantaGate-Webhook/1.0
Signature verification (Node.js):
const crypto = require('crypto')
function verifyVantaSignature(rawBody, signature, projectSecret) { const expected = 'sha256=' + crypto .createHmac('sha256', projectSecret) .update(rawBody) .digest('hex') return crypto.timingSafeEqual( Buffer.from(expected), Buffer.from(signature) ) }
app.post('/webhook/vanta', express.raw({ type: 'application/json' }), (req, res) => { const sig = req.headers['x-vanta-signature'] if (!verifyVantaSignature(req.body, sig, process.env.VANTA_PROJECT_SECRET)) { return res.status(401).json({ error: 'Invalid signature' }) } const event = JSON.parse(req.body) if (event.status === 'APPROVED') { // ✅ Resume agent workflow } else if (event.status === 'REJECTED') { // ❌ Halt - check event.reject_reason } res.json({ received: true }) })
Your Webhook Signing Secret (VANTA_PROJECT_SECRET) is distinct from your API key. Find it in Dashboard → Project Settings.
# Install dependencies
npm install
npm run build
VANTA_API_KEY=YOUR_API_KEY_HERE npm start
{
"mcpServers": { "vantagate": { "command": "npx", "args": ["-y", "@vantagate/mcp-server"], "env": { "VANTA_API_KEY": "YOUR_API_KEY_HERE" } } } }
{
"mcpServers": { "vantagate": { "command": "node", "args": ["/absolute/path/to/dist/index.js"], "env": { "VANTA_API_KEY": "YOUR_API_KEY_HERE" } } } }
X-API-KEY is hashed server-side - VantaGate never stores plaintext keys.slack_webhook_url is sent per-request and purged atomically after the decision. Zero retention.callback_url is validated against private IP ranges (SSRF prevention).MIT - see LICENSE