Agent Security Scanner MCP
v0.4.2io.github.mikehzp/agentvuln
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
transport:stdio
runtime:pypi
Target client
run in your project directory
claude mcp add agentvuln -- uvx agentvulnAdds 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.