MCP.so
Sign In
A

AgentSafe — URL Trust Scoring for AI Agents

@andyscott88

Repository

About AgentSafe — URL Trust Scoring for AI Agents

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.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "agentsafe": {
      "command": "npx",
      "args": [
        "-y",
        "agentsafe-mcp-server"
      ]
    }
  }
}

Tools

3

Check if a URL is safe for an AI agent to interact with. Returns ALLOW, BLOCK, or REQUIRE_HUMAN_APPROVAL with Claude AI reasoning.

Check if a URL is safe for an AI agent to make a payment on. Uses strict payment-context scoring.

Check if a URL is safe for an AI agent to submit login credentials to. Prevents credential theft on phishing sites.

Overview

What is AgentSafe?

AgentSafe is a real-time URL trust scoring tool for AI agents. It blocks phishing, scam sites, and malicious redirects before an agent interacts with them, using six security engines and Claude AI reasoning.

How to use AgentSafe?

—

Key features of AgentSafe

  • 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

Use cases of AgentSafe

  • Protecting AI agents from interacting with malicious websites
  • Preventing phishing and scam URL ingestion during automated browsing
  • Adding a trust layer before agents follow links or submit data
  • Enriching agent workflows with multi-engine URL reputation checks

FAQ from AgentSafe

What security engines does AgentSafe use?

AgentSafe uses six engines: Google Web Risk, VirusTotal, PhishTank, URLhaus, WHOIS domain age, and live SSL.

Does AgentSafe include AI reasoning?

Yes, AgentSafe includes Claude AI reasoning as part of its trust scoring.

What types of URLs does AgentSafe block?

AgentSafe blocks phishing, scam sites, and malicious redirects.

Frequently asked questions

What security engines does AgentSafe use?

AgentSafe uses six engines: Google Web Risk, VirusTotal, PhishTank, URLhaus, WHOIS domain age, and live SSL.

Does AgentSafe include AI reasoning?

Yes, AgentSafe includes Claude AI reasoning as part of its trust scoring.

What types of URLs does AgentSafe block?

AgentSafe blocks phishing, scam sites, and malicious redirects.

Comments

Basic information

Category

AI & Agents

Transports

stdio

Author

andyscott88

Submitted by

andyscott88

More AI & Agents MCP servers

PDI Bridge for Claude

jxrlabs

Connect Claude Desktop to your ServiceNow PDI. Query records, inspect Business Rules, review ACLs, and troubleshoot against your live instance.

UnificAlly MCP

unifically-dev

UnificAlly MCP server. One API for 100+ AI video, image, music and speech models. https://mcp.unifically.com/mcp

Hypnothera

La-Salida

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai

XDC AI

XDC AI is a remote MCP server available at https://xdcai.tech.

bsv.cx

Andy Rowe

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei