English Français العربية

io.github.andyscott88/agentsafe

Official registry AI and agents

Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites.

Source code

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package agentsafe-mcp-server
Claude Code 
claude mcp add agentsafe -e 'AGENTSAFE_API_KEY=<your agentsafe_api_key>' -- npx -y agentsafe-mcp-server@1.0.1
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "agentsafe": {
            "command": "npx",
            "args": [
                "-y",
                "agentsafe-mcp-server@1.0.1"
            ],
            "env": {
                "AGENTSAFE_API_KEY": "<your agentsafe_api_key>"
            }
        }
    }
}

Environment variables

  • AGENTSAFE_API_KEY secret Your AgentSafe API key from agentsafe.app

Frequently asked questions

What is io.github.andyscott88/agentsafe?

Real-time URL trust scoring for AI agents. Blocks phishing and malicious sites.

How do I install io.github.andyscott88/agentsafe?

It runs on your machine. In Claude Code: claude mcp add agentsafe -e 'AGENTSAFE_API_KEY=<your agentsafe_api_key>' -- npx -y agentsafe-mcp-server@1.0.1. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.andyscott88/agentsafe need an API key?

Yes. It expects AGENTSAFE_API_KEY, which you set in its configuration.

Is io.github.andyscott88/agentsafe open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains io.github.andyscott88/agentsafe?

It is published by andyscott88. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.