agent guard MCP
v0.2.1io.github.ipezygj/agent-guard
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
transport:stdio
runtime:pypi
Target client
run in your project directory
claude mcp add agent-guard -- uvx agent-tripwireAdds 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.