AgentSafe — URL Trust Scoring for AI Agents
About
Real-time URL trust scoring for AI agents. Blocks phishing, scam sites, and malicious redirects before your agent interacts with them. 6 security engines including Google Web Risk, VirusTotal, PhishTank, URLhaus, WHOIS domain age, and live SSL — plus Claude AI reasoning.
Details
- Author
- andyscott88
- Downloads
- 130
- Categories
- AI
Jump to
- Real-time URL trust scoring for AI agents
- Blocks phishing, scam sites, and malicious redirects
- Integrates six security engines (Google Web Risk, VirusTotal, PhishTank, URLhaus, WHOIS domain age, live SSL)
- Includes Claude AI reasoning for additional analysis
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AgentSafe — URL Trust Scoring for AI AgentsCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
—
evaluate_url
Check if a URL is safe for an AI agent to interact with. Returns ALLOW, BLOCK, or REQUIRE_HUMAN_APPROVAL with Claude AI reasoning.
evaluate_payment
Check if a URL is safe for an AI agent to make a payment on. Uses strict payment-context scoring.
evaluate_login
Check if a URL is safe for an AI agent to submit login credentials to. Prevents credential theft on phishing sites.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"agentsafe \u2014 url trust scoring for ai agents": {
"agentsafe": {
"command": "npx",
"args": [
"-y",
"agentsafe-mcp-server"
]
}
}
}
}McpServers
{
"agentsafe": {
"command": "npx",
"args": [
"-y",
"agentsafe-mcp-server"
]
}
}Real-time URL trust scoring for AI agents. Blocks phishing, scam sites, and malicious redirects before your agent interacts with them. 6 security engines including Google Web Risk, VirusTotal, PhishTank, URLhaus, WHOIS domain age, and live SSL — plus Claude AI reasoning.
Status: created
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
