AgentGuard — security checks for AI agents MCP
v0.1.2io.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.