Zeqqat
The safe MCP for Dokploy: agents deploy and fix apps without holding keys or seeing secrets.
作者提供的说明(英文原文)
AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.
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。
ANTHROPIC_API_KEY, GOOGLE_WEB_RISK_API_KEY, GOOGLE_SAFE_BROWSING_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 …”。
适用于网页版、桌面版和手机版 Claude:
https://url-safety-validator-mcp-production.up.railway.app打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"url-safety-validator": {
"command": "npx",
"args": [
"-y",
"url-safety-validator-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"GOOGLE_WEB_RISK_API_KEY": "your-value",
"GOOGLE_SAFE_BROWSING_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http url-safety-validator https://url-safety-validator-mcp-production.up.railway.appclaude mcp add url-safety-validator --env ANTHROPIC_API_KEY=your-value --env GOOGLE_WEB_RISK_API_KEY=your-value --env GOOGLE_SAFE_BROWSING_API_KEY=your-value -- npx -y url-safety-validator-mcp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": {
"url-safety-validator": {
"url": "https://url-safety-validator-mcp-production.up.railway.app"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"url-safety-validator": {
"command": "npx",
"args": [
"-y",
"url-safety-validator-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"GOOGLE_WEB_RISK_API_KEY": "your-value",
"GOOGLE_SAFE_BROWSING_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": {
"url-safety-validator": {
"type": "http",
"url": "https://url-safety-validator-mcp-production.up.railway.app"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"url-safety-validator": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"url-safety-validator-mcp"
],
"env": {
"ANTHROPIC_API_KEY": "your-value",
"GOOGLE_WEB_RISK_API_KEY": "your-value",
"GOOGLE_SAFE_BROWSING_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。
ChatGPT 只能连接互联网上的服务器:
https://url-safety-validator-mcp-production.up.railway.app菜单名称可能因套餐和版本不同而略有差异。
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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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 OjasKord 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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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:ANTHROPIC_API_KEY, GOOGLE_WEB_RISK_API_KEY, GOOGLE_SAFE_BROWSING_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(1.2.27)于5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。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Zeqqat, 4da MCP Server, Dependency Vulnerability Tracker — package security advisories ($0.01/query)
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
The safe MCP for Dokploy: agents deploy and fix apps without holding keys or seeing secrets.
Upgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans.
Dependency vulns & malicious-package advisories. Be born in one call — free testnet funds.
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。
Stop your agent from fetching a dangerous URL before it's too late.
Agents that process emails, scrape pages, or consume API responses encounter URLs from untrusted sources constantly. This server gives your agent a single call to gate every URL before it proceeds — returning a SAFE/SUSPICIOUS/DANGEROUS verdict backed by Google Web Risk, Google Safe Browsing, and AI analysis.
One tool: check_url. One call returns:
AI-powered analysis — NOT a simple database lookup.
Call check_url BEFORE your agent:
If the verdict is DANGEROUS — halt. If SUSPICIOUS — flag for review. If SAFE — proceed.
| Source | Type | Coverage |
|---|---|---|
| Google Web Risk | Commercial API | Malware, phishing, unwanted software |
| Google Safe Browsing | Free | Malware, phishing, unwanted software (fallback when Web Risk key absent) |
| RDAP | Free | Domain registration date |
| Anthropic Claude | AI | Trust scoring and reasoning synthesis |
| Tier | Calls | Price |
|---|---|---|
| Free | 10/month | No API key needed |
| Starter | 500-call bundle | $20 |
| Pro | 2,000-call bundle | $70 |
https://url-safety-validator-mcp-production.up.railway.app
Add x-api-key: YOUR_KEY header for Pro/Enterprise tiers. Leave blank for free tier.
npm install -g url-safety-validator-mcp
{
"mcpServers": { "url-safety-validator": { "command": "url-safety-validator-mcp", "env": { "ANTHROPIC_API_KEY": "your-key", "GOOGLE_WEB_RISK_API_KEY": "your-key" } } } }
{
"mcpServers": { "url-safety-validator": { "type": "http", "url": "https://url-safety-validator-mcp-production.up.railway.app" } } }
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({ "url-safety-validator": { "url": "https://url-safety-validator-mcp-production.up.railway.app", "transport": "http" } }) tools = await client.get_tools()
from agents import Agent, HostedMCPTool
agent = Agent( name="Assistant", tools=[HostedMCPTool(tool_config={ "type": "mcp", "server_label": "url-safety-validator", "server_url": "https://url-safety-validator-mcp-production.up.railway.app", "require_approval": "never" })] )
Same as LangChain above — langchain-mcp-adapters works with LangGraph natively.
{
"url": "https://suspicious-domain.xyz/login", "hostname": "suspicious-domain.xyz", "verdict": "DANGEROUS", "trust_score": 4, "ssl_valid": true, "domain_age_days": 12, "redirect_chain_detected": false, "threat_categories": ["phishing", "newly_registered"], "reasoning": "Domain registered 12 days ago and impersonates a financial institution's login page. Google Web Risk flags this as SOCIAL_ENGINEERING.", "ai_confidence": "HIGH", "analysis_type": "AI-powered -- NOT a simple database lookup" }
Results are for informational purposes only. Verdict is a risk signal — not a guarantee of safety or danger. We do not log or store your query content. Full terms: kordagencies.com/terms.html
Provider: Kord Agencies Pte Ltd, Singapore.