Skip to content
mcp/harbor
Claude Code

agentsafe for Claude Code

io.github.andyscott88/agentsafe

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

client:Claude Code transport:stdio runtime:npm

Install agentsafe in Claude Code

run in your project directory

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

claude mcp add agentsafe -e AGENTSAFE_API_KEY=<AGENTSAFE_API_KEY> -- npx -y agentsafe-mcp-server

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

agentsafe in other clients

agentsafe MCP server