SUNGLASSES
Input firewall for AI agents: scan text and files before they're read. Local, no network by default.
作者提供的说明(英文原文)
Fraud Prevention MCP server using FraudLabs Pro API.
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。
FRAUDLABSPRO_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": {
"fraudlabspro": {
"command": "uvx",
"args": [
"mcp-fraudlabspro"
],
"env": {
"FRAUDLABSPRO_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add fraudlabspro --env FRAUDLABSPRO_API_KEY=your-value -- uvx mcp-fraudlabspro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": {
"fraudlabspro": {
"command": "uvx",
"args": [
"mcp-fraudlabspro"
],
"env": {
"FRAUDLABSPRO_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": {
"fraudlabspro": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-fraudlabspro"
],
"env": {
"FRAUDLABSPRO_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9日
注册名称已通过 GitHub 账户 fraudlabspro 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:FRAUDLABSPRO_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(1.1.1)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 Python (uv)。
同一分类中有:SUNGLASSES, KillerSkills, Draugr
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
Input firewall for AI agents: scan text and files before they're read. Local, no network by default.
Security verdicts for agent skills and MCP servers, from sandbox runs, before you install them.
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
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。
An MCP-compliant server that integrates the FraudLabs Pro fraud detection system into AI assistants like Claude Desktop. This server enables real-time screening of order transactions and user-related events (like logins or registrations) to identify and prevent fraudulent activities.
There are two ways to use this MCP server:
Use this if you want to connect directly to the hosted server.
Use this if your MCP client supports remote servers over HTTP. No Node.js or npx is needed.
{
"mcpServers": { "fraudlabspro": { "type": "http", "url": "https://mcp.fraudlabspro.com/", "headers": { "X-API-Key": "YOUR_API_KEY_HERE" } } } }
If your client is configured from the command line, such as Claude Code, you can add the server with:
claude mcp add --transport http fraudlabspro https://mcp.fraudlabspro.com/ --header "X-API-Key: YOUR_API_KEY_HERE"
npxUse this if your MCP client only supports local (stdio) servers. The mcp-remote package runs locally and forwards requests to the hosted server. Node.js is required.
{
"mcpServers": { "fraudlabspro": { "command": "npx", "args": [ "-y", "mcp-remote@latest", "https://mcp.fraudlabspro.com/", "--header", "X-API-Key:YOUR_API_KEY_HERE" ] } } }
Restart your MCP client after saving the changes, and you should see the server appear in the tools menu.
Ensure you have the required libraries installed in your environment:
pip install mcp httpx uv
To use this server with an MCP client (such as Claude Desktop), add the following entry to your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": { "fraudlabspro": { "command": "uvx", "args": [ "mcp-fraudlabspro" ], "env": { "FRAUDLABSPRO_API_KEY": "YOUR_API_KEY_HERE" } } } }
📦 Order Management
| Tool | Description | Key Arguments |
|---|---|---|
| screen_order | Screen an order for fraud. | ip, email, amount, bin_no, bill_country, ship_country |
| get_order_result | Retrieve the validation result for a previous order. | transaction_id |
| feedback_order | Update order status (APPROVE, REJECT, BLACKLIST). | transaction_id, action, note |
👤 User Management
| Tool | Description | Key Arguments |
|---|---|---|
| screen_user | Screen user events like logins or signups. | email, ip, phone, first_name, last_name |
| get_user_result | Retrieve results for a previous user screening. | user_transaction_id |
| feedback_user | Update user event status based on manual review. | user_transaction_id, action, reason |
The server uses FastMCP and sends logs through the MCP context. You can view logs in the Claude Desktop "Developer Console" to inspect outgoing payloads and API responses for debugging.
Common Error: If you receive "An API key is needed," ensure the FRAUDLABSPRO_API_KEY environment variable is correctly set in your configuration file and that you have restarted the MCP client.
See the LICENSE file.