SML Risk Firewall
Pre-trade risk checks for agent trades: orders vs your limits, signed receipts.
作者提供的说明(英文原文)
Detect fake-recruiter and job-offer scams using free OSINT. No API keys.
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": {
"jobverify": {
"command": "uvx",
"args": [
"jobverify-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add jobverify -- uvx jobverify-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"jobverify": {
"command": "uvx",
"args": [
"jobverify-mcp"
]
}
}
}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": {
"jobverify": {
"type": "stdio",
"command": "uvx",
"args": [
"jobverify-mcp"
]
}
}
}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7日
注册名称已通过 GitHub 账户 yessGlory17 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(0.1.0)于4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 Python (uv)。
同一分类中有:SML Risk Firewall, ipdata MCP by usefulapi, MaxMind minFraud MCP by usefulapi
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
Pre-trade risk checks for agent trades: orders vs your limits, signed receipts.
Look up location, network, company and threat data for IP addresses and ASNs in ipdata.
MCP server for MaxMind minFraud — score transactions for fraud risk from your AI assistant.
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。
Check whether a recruiter or job offer is real — before you reply.
You get a message: *"We loved your profile and want to offer you a great remote job."* It sounds real. The company has a logo. The recruiter has a photo. But something feels off.
JobVerify helps you find out — in seconds — whether it's genuine or a scam.
You paste the recruiter's message (or a company name, a link, or an email) and ask your AI assistant. JobVerify quietly runs the same background checks a professional investigator would, then gives you a plain-English answer: looks legit, be careful, or this is almost certainly a scam — and *why*.
Fake recruiter and job-offer scams are everywhere, and they're convincing. On your own, you're left guessing:
By the time you notice, your time, your personal details — or your money — may already be gone.
JobVerify cross-checks the offer against dozens of free, public information sources and combines the clues into one clear verdict:
No account, no sign-up, and none of your data is sold or stored. It simply helps you not get fooled.
You don't need to learn anything technical. It's a three-step conversation:
[!NOTE]
JobVerify never logs into or scrapes LinkedIn. It only looks at information that is already
public, and reads website history through the Internet Archive — the safe, legal way to check
how long a profile or company page has *really* existed (scammers rely on brand-new throwaway accounts).
Think of it as a checklist a careful friend — who happens to be a fraud investigator — would run for you:
| Area | The question it answers |
|---|---|
| The message | Does this match known scam playbooks (advance fees, fake tasks, crypto, urgency)? |
| The company | Is it a real, registered business? Any recent scam reports? Is the office address real? |
| The person | Is the email real and deliverable? Is the phone valid? Are the photos/usernames reused elsewhere? |
| The links | Is the domain brand-new? A look-alike of a real brand? On any phishing/malware blocklist? |
| The money | Is the crypto wallet they gave you already flagged in scam databases? |
| The history | How long has this profile or website *actually* been online? |
Ask your assistant something as simple as:
Is this recruiter legit?
"Hi! I'm a talent partner at Example Corp. We loved your profile and want to offer you a remote role at $45/hr. To get started, please purchase $200 of onboarding equipment through this link — you'll be fully reimbursed on day one. Let's continue on Telegram: @examplecorp_hr"
JobVerify will pick out Example Corp, the link, and the Telegram hand-off, check each one, and reply with something like: *"⚠️ High risk — the company has no public registration, the link was registered 4 days ago, and asking you to pay upfront and move to Telegram are textbook scam signals."*
No cloning. No virtualenv. No manual install. JobVerify runs straight from GitHub — you only paste a few lines into your AI assistant's config, and it fetches and launches itself on demand.
[!NOTE]
The only thing you need once is uv — a tiny, free helper that runs
the tool for you:
- macOS / Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Windows:
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
Add this to your claude_desktop_config.json, then restart Claude:
{
"mcpServers": { "jobverify": { "command": "uvx", "args": ["jobverify-mcp"] } } }
One line in your terminal:
claude mcp add jobverify -- uvx jobverify-mcp
The first run takes a few seconds while it downloads the tool; after that it's instant.
Paste a suspicious message and ask *"Is this offer legit?"* — or run the built-in `analyze` prompt. That's it.
For the curious: the full toolbox
Under the hood, the AI assistant orchestrates these individual checks (all free, no keys):
| Tool | What it checks |
|---|---|
extract_entities | Pulls emails, links, phones, wallets, and profile URLs out of a message |
check_scam_patterns | Matches text against known scam tactics |
check_email / check_email_footprint | Email deliverability + linked social accounts |
check_domain / check_domain_auth | Domain age, registrar, and whether it can be spoofed |
check_typosquatting / find_lookalike_domains | Look-alike / imposter domains |
check_url / check_ip | Phishing & malware blocklists |
check_certificate_transparency | A site's certificate & subdomain history |
parse_email_headers | Origin, SPF/DKIM/DMARC, and mismatches in raw email headers |
check_phone | Phone number validity and region |
check_crypto_address | Known-scam crypto wallet databases |
verify_company / search_company_news / verify_address | Business registration, press, and real address |
check_github_org / check_username | Whether an org/username really exists and how old it is |
check_wayback / fetch_archived_page | Internet Archive history & content (the legal way to read a page) |
There's also a single `analyze` prompt that runs the whole extract → check → verdict flow for you.
JobVerify is a decision-support tool. Its signals are probabilistic and may be incomplete or wrong. Always use your own judgment, and never treat a result as a definitive statement about any individual or organization.
MIT — use it, share it, and help people stay safe.