Skip to content
mcp/harbor
Verified official

agentshield mcp MCP

v0.1.3

io.github.dl-eigenart/agentshield-mcp

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

transport:stdio runtime:npm
View source

Target client

run in your project directory

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

claude mcp add agentshield-mcp -e AGENTSHIELD_API_KEY=<AGENTSHIELD_API_KEY> -- npx -y @eigenart/agentshield-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.