AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.
This MCP server provides an AI URL safety validator for gating untrusted URLs before an agent fetches them. It returns a SAFE/SUSPICIOUS/DANGEROUS verdict and includes a trust score and threat-intelligence support. It is designed for scenarios where agents encounter URLs from emails, scraped pages, or API responses.
🛠️ Key Features
Single tool call to validate URLs before processing
SAFE/SUSPICIOUS/DANGEROUS verdict output
Trust score included with results
Threat-intelligence backing (Google Web Ri…)
🚀 Use Cases
Prevent an agent from fetching dangerous URLs
Validate URLs found in emails
Validate URLs from scraping workflows
Validate URLs from API responses
⚡ Developer Benefits
Centralized URL gating for agents
Reduces unsafe network requests from untrusted inputs
Security-focused integration for MCP-agent pipelines
⚠️ Limitations
Tooling is limited to 1 tool as indicated by toolCount=1
Checks a URL for phishing, malware, typosquatting, and redirect threats. Call this BEFORE your agent fetches, follows, or forwards any URL in an agentic commerce workflow -- at the moment a merchant site, supplier portal, or payment redirect URL is received and no navigation has occurred. Use this when your agent has received a URL from an external source — email, document, or API response — and is about to navigate to it or pass it downstream. Checks live against Google Web Risk (webrisk.googleapis.com) and Google Safe Browsing (safebrowsing.googleapis.com). Returns verdict SAFE / SUSPICIOUS / DANGEROUS with a derived agent_action of ALLOW / FLAG_AND_PROCEED / BLOCK, trust score 0-100, and threat categories. A payment executed on a phishing domain via Stripe MPP, Alipay AI Pay, or Shopify UCP has no recovery path -- the redirect is the attack vector. A DANGEROUS verdict means halt immediately. Returns machine-ready verdict, no further analysis needed.
Parameters1
url
string
required
The URL to check. Full URL preferred (e.g. https://example.com/path). Bare domains also accepted.
Raw schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to check. Full URL preferred (e.g. https://example.com/path). Bare domains also accepted."
}
},
"required": [
"url"
]
}
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.
Same as LangChain above — langchain-mcp-adapters works with LangGraph natively.
Example Response
json
{"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"}
Legal
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.
Install
Tools (1)
check_url
Configuration
Environment variables
ANTHROPIC_API_KEYrequiredsecret
Anthropic API key for AI trust scoring
GOOGLE_WEB_RISK_API_KEYsecret
Google Web Risk API key (commercial). Degrades gracefully without it.
GOOGLE_SAFE_BROWSING_API_KEYsecret
Google Safe Browsing API key (free tier available).
