{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/29fb1cddcb624412a512e4aa0c930e1b\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/29fb1cddcb624412a512e4aa0c930e1b-8d47a3729acd4f54.gif","duration":250.134,"title":"Guard Rails MCP, Securing Your AI Agents","description":"Hi, I am Vincent, and this is Guard Rails MCP. It is a gateway that monitors and controls any AI or API key in your software, blocking anything that does not pass the rules you set. From a single dashboard, you get agent status, kill switches, approvals in progress, denied actions, and daily security findings with a downloadable report. You can set policies for what should always ask permission, never do, or always allow. There is action requested, you can approve or deny security prompts, and you can toggle kill switches to pause agents."}