Runtime Guard is a free, local-first MCP server that enforces policy on file and shell actions before execution. No account required.
It provides a local GUI for easy policy configuration, flags dangerous content at write time and blocks at execution and it offers a single-button security posture config for AI agents.
Update: shipped v1.2 today — major GUI overhaul and improved policy logic. Container version coming early next week which should remove most of the install friction people hit. Changelog on GitHub if you want the details
Thank you. It was a very interesting development and testing, it's amazing to see the models learn in realtime that there's a protection layer and sometimes they say they expect a command to fail because of it even before it runs. Amazing but scary at the same time. While the tool still has a lot of room for improvement, I'm looking forward to add additional features as quickly as I can.