Spree Commerce: open-source B2B and marketplace ecommerce
Open-source B2B and marketplace ecommerce; new stores include an MCP server for AI agents.
作者提供的说明(英文原文)
Runtime security for AI agent commerce. CLI + MCP server blocks hallucinated purchases.
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。
POP_CDP_URL, POP_ALLOWED_CATEGORIES, POP_MAX_PER_TX, POP_MAX_DAILY, POP_GUARDRAIL_ENGINE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": {
"pop-pay": {
"command": "npx",
"args": [
"-y",
"pop-pay"
],
"env": {
"POP_CDP_URL": "your-value",
"POP_ALLOWED_CATEGORIES": "your-value",
"POP_MAX_PER_TX": "your-value",
"POP_MAX_DAILY": "your-value",
"POP_GUARDRAIL_ENGINE": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add pop-pay --env POP_CDP_URL=your-value --env POP_ALLOWED_CATEGORIES=your-value --env POP_MAX_PER_TX=your-value --env POP_MAX_DAILY=your-value --env POP_GUARDRAIL_ENGINE=your-value -- npx -y pop-pay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": {
"pop-pay": {
"command": "npx",
"args": [
"-y",
"pop-pay"
],
"env": {
"POP_CDP_URL": "your-value",
"POP_ALLOWED_CATEGORIES": "your-value",
"POP_MAX_PER_TX": "your-value",
"POP_MAX_DAILY": "your-value",
"POP_GUARDRAIL_ENGINE": "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": {
"pop-pay": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"pop-pay"
],
"env": {
"POP_CDP_URL": "your-value",
"POP_ALLOWED_CATEGORIES": "your-value",
"POP_MAX_PER_TX": "your-value",
"POP_MAX_DAILY": "your-value",
"POP_GUARDRAIL_ENGINE": "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。
POP_CDP_URL envPOP_ALLOWED_CATEGORIES envPOP_MAX_PER_TX envPOP_MAX_DAILY envPOP_GUARDRAIL_ENGINE 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8日
注册名称已通过 GitHub 账户 100xPercent 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(0.5.7)于7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:Spree Commerce: open-source B2B and marketplace ecommerce, Stripe MCP, MCP Cn Commerce
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
Open-source B2B and marketplace ecommerce; new stores include an MCP server for AI agents.
MCP server integrating with Stripe - tools for customers, products, payments, and more.
8 read-only MCP platform entries; support is operation-specific; merchant live acceptance pending
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。
it only takes 0.1% of Hallucination to drain 100% of your wallet.
The runtime security layer for AI agent commerce. Drop-in CLI + MCP server. Card credentials are injected directly into the browser DOM via CDP — they never enter the agent's context window. One hallucinated prompt can't drain a wallet it can't see.
📄 Research Dataset & Reproduction — this repository hosts the open dataset and reproduction harness for *"The Illusion of Single-Attacker Rankings"*. research: jump to Research Dataset & Reproduction.
Choose your preferred method:
Homebrew (macOS)
brew install 100xpercent/tap/pop-pay
curl (Linux / macOS) — bootstraps via npm; requires Node.js 18+
curl -fsSL https://raw.githubusercontent.com/100xPercent/pop-pay/main/install.sh | sh
npm (global)
npm install -g pop-pay
npx (no install — one-off runs)
npx -y pop-pay <command>
All install paths expose the same binaries: pop-pay, pop-launch, pop-init-vault, pop-unlock.
Also available as
@100xpercent/mcp-server-pop-pay— identical package under the MCP@scope/mcp-server-convention. Tracks the same version on every release.
Using Python? Check out pop-pay-python —
pip install pop-pay. Same security model, same vault format, independent release cycle — safe to switch between runtimes.
pop-pay init-vault
This encrypts your card credentials into ~/.config/pop-pay/vault.enc (AES-256-GCM). For stronger protection (blocks agents with shell access):
pop-pay init-vault --passphrase # one-time setup
pop-pay unlock # run once per session
pop-pay launch
This opens a Chromium instance on http://localhost:9222 that pop-pay injects credentials into. Your agent (via MCP, browser automation, or x402) then drives the checkout flow — card details never leave the browser process.
The CLI launches infrastructure; the actual payment tool calls come from your agent. Two supported paths:
Full CLI reference: pop-pay --help.
Standard config for any MCP-compatible client:
{
"mcpServers": { "pop-pay": { "command": "npx", "args": ["-y", "pop-pay", "launch-mcp"], "env": { "POP_CDP_URL": "http://localhost:9222" } } } }
Claude Code
Claude Code uses its own CLI — the JSON config above is not needed.
claude mcp add --scope user pop-pay -- npx -y pop-pay launch-mcp
--scope user makes it available across all projects. To remove: claude mcp remove pop-pay
Cursor / Windsurf / VS Code
Add the JSON config above to:
~/.cursor/mcp.json~/.codeium/windsurf/mcp_config.json.vscode/mcp.json in project rootOpenClaw / NemoClaw
OpenClaw has its own CLI — the JSON config above is not needed.
openclaw mcp add pop-pay -- npx -y pop-pay launch-mcp
Or add to ~/.openclaw/mcp_servers.json using the JSON config above.
For System Prompt templates and NemoClaw sandbox setup, see Integration Guide §4.
Docker
docker-compose up -d
Runs the MCP server + headless Chromium with CDP. Mount your encrypted vault from the host.
| Tool | Description |
|---|---|
request_virtual_card | Issue a virtual card and inject credentials into the checkout page via CDP. Automatically scans the page for hidden prompt injections. |
request_purchaser_info | Auto-fill billing/contact info (name, address, email, phone). Automatically scans the page for hidden prompt injections. |
request_x402_payment | Pay for API calls via the x402 HTTP payment protocol. |
Tip for Claude Code users: Add the following to your project's
CLAUDE.mdto help the agent know when to call pop-pay:
*"When you encounter a payment form or checkout page, use the
request_virtual_cardtool. For billing/contact info forms, userequest_purchaser_infofirst."*
Core variables in ~/.config/pop-pay/.env. See ENV_REFERENCE.md for the full list.
| Variable | Default | Description |
|---|---|---|
POP_ALLOWED_CATEGORIES | ["aws","cloudflare"] | Approved vendor categories — see Categories Cookbook |
POP_MAX_PER_TX | 100.0 | Max USD per transaction |
POP_MAX_DAILY | 500.0 | Max USD per day |
POP_BLOCK_LOOPS | true | Block hallucination/retry loops |
POP_AUTO_INJECT | true | Enable CDP card injection |
POP_GUARDRAIL_ENGINE | keyword | keyword (zero-cost) or llm (semantic) |
keyword (default) | llm | |
|---|---|---|
| Mechanism | Keyword matching on reasoning string | Semantic analysis via LLM |
| Cost | Zero — no API calls | One LLM call per request |
| Best for | Development, low-risk workflows | Production, high-value transactions |
To enable LLM mode, see Integration Guide §1.
| Provider | Description |
|---|---|
| BYOC (default) | Bring Your Own Card — encrypted vault credentials, local CDP injection. |
| Stripe Issuing | Real virtual cards via Stripe API. Requires POP_STRIPE_KEY. |
| Lithic | Multi-issuer adapter (Stripe Issuing / Lithic). |
| Mock | Test mode with generated card numbers for development. |
Priority: Stripe Issuing → BYOC Local → Mock.
| Layer | Defense |
|---|---|
| Context Isolation | Card credentials never enter the agent's context window or logs |
| Encrypted Vault | AES-256-GCM with XOR-split salt and native scrypt key derivation (Rust) |
| TOCTOU Guard | Domain verified at the moment of CDP injection — blocks redirect attacks |
| Repr Redaction | Automatic masking (****-4242) in all MCP responses, logs, and tracebacks |
See THREAT_MODEL.md for the full STRIDE analysis and COMPLIANCE_FAQ.md for enterprise details.
This repository hosts the open-source dataset and harness for the cross-vendor attacker-stability methodology described in the corresponding research paper. Reviewer/researcher reproduction artifacts:
tests/redteam/corpus/attacks.json — full payload set with category labelsGENERATION.md — corpus generation protocolschema.json — payload schematests/redteam/runs/runs/adaptive/2026-04-28T19-50-*runs/static/runs/ablation/tests/redteam/runs/MANIFEST.sha256 — byte-level integrity for all artifactspaper-artifacts/croissant.jsonpython3 paper-artifacts/gen-tables.py --table all — Tab.~bypassk / threat-ablation / cross-vendorpython3 paper-artifacts/gen-taxonomy-map.py — Fig.~taxonomy-mapFor dataset schema, statistical methodology (bootstrap CI, Holm-Bonferroni, McNemar), full from-scratch re-collection instructions, JSONL row data dictionary, and responsible-disclosure policy, see [docs/PAPER_REPRODUCTION.md](docs/PAPER_REPRODUCTION.md).
MIT