io.github.andyscott88/agentsafe

io.github.andyscott88/agentsafe·v1.0.1·Calendar & Time

Quality Score

/100

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

Repository →

§00 Trust verdict · v1 advisory · method

UNVERIFIEDno verdict on file

Verdict not yet evaluated for this tool. The hybrid eval runs adversarial cases first; coverage rolls out as the corpus expands. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: hybrid eval, four-state verdict, honest limits.

§01 Install

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "agentsafe": {
      "command": "npx",
      "args": [
        "-y",
        "agentsafe-mcp-server"
      ],
      "env": {
        "AGENTSAFE_API_KEY": "<your-agentsafe_api_key>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "agentsafe": {
      "command": "npx",
      "args": [
        "-y",
        "agentsafe-mcp-server"
      ],
      "env": {
        "AGENTSAFE_API_KEY": "<your-agentsafe_api_key>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)