Skip to content
Verified official

AgentGuard — security checks for AI agents MCP

v0.1.2

io.github.shuaicongxiaomai/agentguard

Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).

transport:stdio runtime:oci

Target client

run in your project directory

claude mcp add agentguard -- docker run -i --rm ghcr.io/shuaicongxiaomai/agentguard:0.1.2

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.