原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

SafePay Check

作者:NovaCorpAI版本 0.8.1i★ 0i在云端运行官方网站 ↗
注册名称com.agentposhq.safepay/check

安装方法

What it does

Judges a payment (PayPal, PYUSD or USDC) before an AI agent makes it. Signed proof. Moves no money.

  • Connects 在云端运行
  • Account or key Needs Authorization
  • Category 网店与支付

为什么排在这里

此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列

1. 在 Claude 连接器目录中否
2. 团队实测过否
3. 适合泰国用户否
4. 不计星标的使用量20/100热度 0 · 新鲜度 12 · 仍在响应 8 · 用户喜欢 +0
5. 登记日期2026-11-08

用户喜欢: 0 · 最多加 5 分(每人 1 分),不能用钱买。

质量: 基础检查通过 4/4 项(仅展示,不用于排序)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 SafePay Check。按照 https://mcp.popnx.com/i/agentposhq-safepay-check.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 4/4 项检查 · 你的提问会经过开发者的服务器(safepay.agentposhq.com) · ✓ 命令已检查 2026年11月13日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude · 约 5 分钟

需要 SafePay Check 的密钥(在开发者网站创建) · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 注册并创建 SafePay Check 的密钥

    打开开发者网站,注册账户并创建 API 密钥,下一步要用。价格和免费方案请看开发者网站。

    打开 SafePay Check 网站 ↗

  2. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  3. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称SafePay Check
    Remote MCP server URL · 地址https://safepay.agentposhq.com/mcp

    在 Request headers 下添加这个名称和值

    Header 名称Authorization
    值Bearer <在这里粘贴你的密钥>

    只把密钥粘贴到应用的输入框里,不要粘贴到聊天中或发给任何人

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  4. 在聊天中开启

    +ConnectorsSafePay Check

  5. 试一试

    用 SafePay Check 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 SafePay Check,或回答中出现 SafePay Check 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

ChatGPT 暂时无法连接 SafePay Check

SafePay Check 连接时需要你自己的密钥,但 OpenAI 帮助页面只说明了 OAuth 登录,没有我们能核实的填密钥方式

你可以改用这些方式

A · 使用能连接 SafePay Check 的应用

  • 需要 SafePay Check 的密钥(在开发者网站创建) · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
  • 需要 SafePay Check 的密钥(在开发者网站创建)
  • 需要 SafePay Check 的密钥(在开发者网站创建)
  • 需要 SafePay Check 的密钥(在开发者网站创建)

B · 网店与支付 类中能连接 ChatGPT 的其他服务器

从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的

可连接 Claude Code · 约 5 分钟

需要 SafePay Check 的密钥(在开发者网站创建)

  1. 注册并创建 SafePay Check 的密钥

    打开开发者网站,注册账户并创建 API 密钥,下一步要用。价格和免费方案请看开发者网站。

    打开 SafePay Check 网站 ↗

  2. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  3. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user check https://safepay.agentposhq.com/mcp --header 'Authorization: Bearer your-value'

    按 Enter 前,把“your-value”改成你的密钥

    只把密钥粘贴到应用的输入框里,不要粘贴到聊天中或发给任何人

  4. 在 Claude Code 中输入 /mcp

    应能看到 SafePay Check 在列表中并显示已连接

  5. 试一试

    用 SafePay Check 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 SafePay Check,或回答中出现 SafePay Check 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor · 约 5 分钟

需要 SafePay Check 的密钥(在开发者网站创建)

  1. 注册并创建 SafePay Check 的密钥

    打开开发者网站,注册账户并创建 API 密钥,下一步要用。价格和免费方案请看开发者网站。

    打开 SafePay Check 网站 ↗

  2. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  3. 填写你的密钥

    在 SafePay Check 的设置中,Authorization 还是空的,填入你的密钥并保存

    只把密钥粘贴到应用的输入框里,不要粘贴到聊天中或发给任何人

  4. 在 Cursor 中以 Agent 模式打开 AI 聊天

  5. 试一试

    用 SafePay Check 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 SafePay Check,或回答中出现 SafePay Check 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code · 约 5 分钟

需要 SafePay Check 的密钥(在开发者网站创建)

  1. 注册并创建 SafePay Check 的密钥

    打开开发者网站,注册账户并创建 API 密钥,下一步要用。价格和免费方案请看开发者网站。

    打开 SafePay Check 网站 ↗

  2. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  3. 填写你的密钥

    在 SafePay Check 的设置中,Authorization 还是空的,填入你的密钥并保存

    只把密钥粘贴到应用的输入框里,不要粘贴到聊天中或发给任何人

  4. 在 VS Code 中以 Agent 模式打开 AI 聊天

  5. 试一试

    用 SafePay Check 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 SafePay Check,或回答中出现 SafePay Check 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://safepay.agentposhq.com/mcp

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 SafePay Check 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user check https://safepay.agentposhq.com/mcp --header 'Authorization: Bearer your-value'

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "check": {
      "url": "https://safepay.agentposhq.com/mcp",
      "headers": {
        "Authorization": "Bearer your-value"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "check": {
      "type": "http",
      "url": "https://safepay.agentposhq.com/mcp",
      "headers": {
        "Authorization": "Bearer your-value"
      }
    }
  }
}

需要你填写的值

  • Authorization 机密 必填 HTTP header
    Bearer spk_... agent key, free at https://safepay.agentposhq.com/connect

说明仍为英文原文。

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。

一览

每周下载量i
不在 npm/PyPI 上
已验证域名
✓ safepay.agentposhq.com
连接方式
在云端运行
传输方式
streamable-http
最新版本i
0.8.1
发布到注册中心i
2026年11月8日
代码最后更新i
2026年11月12日
最近检查
2026年11月14日
作者
NovaCorpAI
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月14日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。

  • safepay_check_payment

    Checks a planned payment before it is made. Judges the merchant, amount and task against the account's payment rules, the payee's payment history, a live web check of the merchant and an intent check, and returns allow, hold or block with the reasons, a check id and a signed atte

  • safepay_verify

    Verifies a SafePay seal id (SP-XXXXXXXXXX), a signed receipt or a precheck attestation against SafePay's published Ed25519 key. Returns whether it is genuine and intact, and what it states.

  • safepay_verify_settlement

    Reads a Stellar transaction from the public ledger (Horizon) and compares it with a SafePay precheck attestation: whether it succeeded, paid the approved payee, in Circle's USDC, no more than the approved amount, while the check was valid. Returns the findings and a signed result

  • safepay_policy

    Returns the payment rules this account is judged under, in plain words, with their fingerprint.

  • safepay_recent_checks

    Returns this account's latest payment checks: verdict, merchant, amount and time.

基础检查i

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19日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 safepay.agentposhq.com 验证(注册中心会核实域名所有权)

  • ✓ 通过

    仍在维护

    代码最后更新于7天前

  • – 不适用

    有许可证

    不适用:由 safepay.agentposhq.com 的所有者自己运行的云端服务器,你不会运行仓库里的代码

  • ✓ 通过

    端点有响应

    在 164 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 5 个工具描述,未发现针对 AI 的隐藏指令

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/agentposhq-safepay-check.svg)](https://mcp.popnx.com/en/servers/agentposhq-safepay-check)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“网店与支付”中的其他服务器比较i

  • 星标数多于此分类中其他 2919 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 2919 个服务器的 74% 更新
  • 基础检查结果等于或优于此分类中其他 2919 个服务器的 99%

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。

常见问题

SafePay Check 安全吗?

它在 4 项适用的基础检查中通过了 4 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。

它需要哪些密钥或代码?

你需要填写:Authorization

它在我的电脑上运行还是在云端?

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。

它还在维护吗?

GitHub 仓库最后更新于7天前,最新版本(0.8.1)于11天前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:Stripe MCP, flightclaw, Trade It, Marketplace Ad Pros: Amazon Ads & Seller Central, idealo MCP Server

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

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

Stripe MCP

MCP server integrating with Stripe - tools for customers, products, payments, and more.

作者:stripe广泛使用★ 207213个月前更新

在云端运行✓ 服务方 · stripe.com

flightclaw

Search ~300 airlines and book flights with a checkout link. OAuth sign-in by email code.

作者:flightclaw正在增长★ 862个月前更新

在云端运行✓ 服务方 · flightclaw.com

Trade It

Connect brokerage accounts to AI assistants: holdings, orders, asset lookup, and approved trading.

作者:trade-it-inc起步阶段★ 6234天前更新

在云端运行✓ 服务方 · tradeit.app

idealo MCP Server

Search products, compare prices and discover deals across 6 European markets with your AI assistant.

作者:idealo起步阶段★ 286个月前更新

在云端运行✓ 服务方 · mcp.idealo.com
与相似项目对比
本项
SafePay Check
Stripe MCPflightclawTrade ItMarketplace Ad Pros: Amazon Ads & Seller Centralidealo MCP Server
运行位置在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥是否否否否否
可在 Claude 中按 + 添加否是否否否否
基础检查4/44/44/45/54/44/4
许可证MITMITMITCC0-1.0MITMIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

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。

SafePay

The firewall any AI agent plugs in before it pays with PayPal. SafePay is not another agent: it is the layer under all of them. Whatever the agent is built with (an MCP client such as Claude or Cursor, the PayPal Agent Toolkit, LangChain, plain Python or HTTP), every payment it wants to make passes through SafePay, which decides before any money moves whether to allow, hold, or block it. It checks the payee on the live web, catches lookalike vendors, inflated invoices and injected instructions, holds what a person should see, pays the rest through PayPal, and leaves a signed link in a hash chain for every decision. And it is measured: a reproducible benchmark of real attacks on a wallet-holding agent, not a claim. On the same 17 attacks, spending limits alone stop 4; SafePay stops 16, and all 17 with the new-payee hold, with no legitimate invoice blocked.

Built for accounts payable, not shopping carts. A budget or spending mandate answers *how much* an agent may spend. Most fraud against a business is a payment of a normal size to the wrong payee or for the wrong reason: the invoice email that says "we changed our bank details", a real vendor's name on a lookalike domain, an instruction hidden in the invoice, a payment that sits inside every limit but does not serve the task. Those are the cases SafePay judges: *to whom* and *why*. It composes with limits; it does not replace them.

Built for the PayPal AI Hackathon (Agentic Commerce and Autonomous Payments) by NovaCorp Labs.

We are looking for pilot teams and partners. If you build agents that pay, run accounts payable, or work on payments or fraud and want to try SafePay with your own flows, write to security@novacorplabs.com. Pilots are free and onboarded by hand.

Watch the 2:44 demo video: https://youtu.be/UMra3qDSNEs (English subtitles; the same story as the 3-click tour below).

Judge in 3 clicks

https://safepay.agentposhq.com · no login, no keys; every PayPal call goes to the real PayPal sandbox, and the web check (Tavily) and the reasoning (NVIDIA Nemotron on Nebius) run live. Each browser gets its own session.

Short on time? [Take the 3-minute tour](https://safepay.agentposhq.com/?tour=1): ten steps across the real pages (not a demo page), with a button that runs the scenarios or the chain check for you. Arrow keys move, Esc ends it.

  1. Console → type a policy in plain words → Draft → Apply. For example "Up to $500 per payment and $1,000 a day. Ask me before anything over $300. No gambling or crypto." Nemotron drafts the rules; you see every field before it applies, and the change is chained as a policy link.
  2. Run demo scenarios. Seven payments resolve one by one: a real Notion invoice paid; the same invoice to a lookalike domain blocked; a USD 900 charge blocked by the cap; a casino payout held (the web found a scam complaint, the reasoning found it does not serve the task: open each check to see the sources); two cloud invoices over your "ask me" line held for you (approve one, here or with the Telegram card; every paid card links its public seal page); the last one blocked by the daily cap. Then Create the order through the gate: a real PayPal Agent Toolkit order, created only because SafePay allowed it.
  3. Ledger → Tamper (demo) → Verify chain. Every decision is a link in a signed hash chain; edit one row (on a copy) and the badge turns red. The Flow page replays the same chain as pulses through the layers.

Run it yourself: pip install safepay && safepay --demo (no keys needed).

The five judging criteria, one line each, with where the evidence is:

CriterionWhere to look
Technological implementationPayouts, Orders v2 authorize/capture/void, Vault v3, Transaction Search and webhooks, all against the real sandbox; the Agent Toolkit gated; Nemotron and Tavily live; 504 offline tests at 98% coverage (Tests)
DesignOne console that an operator sets up in plain words and a judge works end to end: policy, scenarios, approvals, Telegram, ledger, Studio, seals, kit (See it)
Potential impactThe fraud is named and sized (IC3, AFP), the 2026 agent incidents are real, and SafePay runs inside a product with real users whose counters are public (The problem, Impulsa)
InnovationJudgment beyond caps (spending limits alone stop 4 of 17 attacks, SafePay 17): the payee on the live web, the task the agent was given, a measured attack benchmark a judge reruns live, a seal the payee verifies without us, AP2 mandates on PayPal authorizations (Attack benchmark, The seal)
PresentationThe 3-minute tour inside the real console, the 2:44 video, and this README: what is real and what is not, stated before the claims (What is real)

See it

Screenshots from the hosted demo (https://safepay.agentposhq.com), real sandbox payouts, real web and model checks.

The Flow. Every payment travels as a pulse through the layers; the page replays the real links of the audit chain and animates new ones as they land.

The Ledger. The hash chain as an AG Grid table (Community edition). Click a link and a full-width detail row opens under it with every check it was judged on, its reasons, its seal and PayPal batch, and the hash of the link before it (marked "matches" or "break"). Verdict chips, a search box and a click on any of the three AG Charts (verdict mix, approved spend per agent, average risk by category) all drive one filter, so the grid, the pinned totals row (released vs stopped, outside the firewall, chain breaks) and the CSV export with full hashes always agree on what is shown. The grid is also the operator's desk: a pinned Act column approves or rejects a held payment, or freezes and resumes an agent, from its row.

Ask the chain (AG Studio). /studio turns the whole audit chain into an AG Studio report: a links table and a checks table (joined on the link), a benchmark-cases table and a mandate-stages table derived from the same records, measures for money released and stopped, holds, blocks, average risk and failed checks, and five finished pages plus a blank one: Overview (what SafePay let through and stopped), Checks (which checks catch what), Timeline (released vs stopped per day as a stacked area, holds and blocks per day, value tiles with day sparklines, a gauge of average risk), Benchmark (every attack-benchmark case the console ran against this deployment: caught, missed, allowed, false alarms, by category and by mode, with each case's step verdicts) and Mandates (a funnel of USD authorized, captured and voided, a pivot of amount by agent and link type). Its assistant is NVIDIA Nemotron 3 Ultra on Nebius, wired through AG Studio's own Direct LLM Runner and OpenAI-Responses adapter to a server proxy that holds the key, pins the model and keeps its own daily cap. One focused analyst agent with five Studio tools (view schema, view page, run a query, add and position a widget) answers "how much did SafePay stop, by verdict and agent, and which checks caused it?" in about six turns, from the data; it has no tool that pays, approves or changes a decision.

Proof. /proof lists every PayPal sandbox object the chain says SafePay created (payout batches, orders, authorizations, captures) in an AG Grid, and "Ask PayPal" re-reads each one from PayPal's own API, so the status shown is PayPal's, not ours. The page also maps every PayPal API SafePay calls to the code that calls it.


What is real and what is not

So nobody has to guess.

Real.

  • PayPal. Every payout, order, authorization, capture, void, vault token, webhook and reconciliation goes to PayPal's sandbox API: the real API, with test money. The host is pinned to the sandbox in config.py; nothing here has ever moved real money. Without PayPal keys the console says "PayPal simulated" and payouts are simulated, and says so on every result.
  • The checks. The web check is a live Tavily search; the reasoning check is Nemotron on Nebius. Both are cached for 24 hours and capped by a daily budget that fails closed. Without keys they are skipped, and the result says "skipped".
  • The evidence. The HMAC-signed hash chain, the Ed25519 seals and the operator's P-256 signatures (WebCrypto, non-extractable) are real keys; seals and receipts verify offline against the published key.
  • The state. Supabase holds the chain, the ledger, approvals, policies and agent keys on the hosted demo; locally it is memory.
  • The numbers. The attack benchmark and the duplicate-submission benchmark are real runs, committed with their runners and raw results, and the console reruns the attack cases live. The cost per decision is measured on those runs.
  • In production. Impulsa is a real product with real micro-businesses; SafePay's history rules run there on every supplier document. The live counters at /api/impact are aggregates with the team's test accounts excluded, and they start at zero: zeros are shown as zeros. Businesses the team owns (AgentPOS, the foundation) that record their real supplier purchases are counted apart and named as ours: real use, not traction. The AgentPOS catalog and quotes come from a real store; the USDC settlement check was run against a real payment on Stellar mainnet.
  • Upstream. paypal/agent-toolkit#124 is a real pull request. It is open, not merged.

Not real, by design.

  • No money. Sandbox only, always.
  • The cases are ours. The 7 demo scenarios, the sample invoices and the 25 benchmark cases were written by us: realistic shapes, fictional vendors on .example addresses (the legitimate vendors carry their real domains so the directory check is meaningful). No customer data anywhere in the repo.
  • The human. Whoever clicks Approve (or answers in Telegram, or presses the kit's button) is the human in the loop. Operator actions are open on the public demo so a judge needs no setup; SAFEPAY_OPERATOR_TOKEN locks them in a real deployment.
  • The kit. safepay-kit is tested end to end against the real console with the keyboard standing in for the buttons. Its GPIO board follows gpiozero and the pins in docs/kit.md, but has not been run on a Raspberry Pi yet.
  • The dispute switch. The CUSTOMER.DISPUTE.* webhook pa

只显示了开头部分;其余内容请在仓库中阅读