Skip to content
mcp/harbor
Verified official

agent security scanner mcp MCP

v2.0.1

io.github.sinewaveai/agent-security-scanner-mcp

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

transport:stdio runtime:npm
View source

Target client

run in your project directory 

claude mcp add agent-security-scanner-mcp -- npx -y agent-security-scanner-mcp

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

This listing does not declare its tools. Connect the server and your client will discover them on the handshake.