{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/6fff31cb4ab34efe86d8082bcfcf7659\" frameborder=\"0\" width=\"1110\" height=\"832\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":832,"width":1110,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":832,"thumbnail_width":1110,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/6fff31cb4ab34efe86d8082bcfcf7659-895c02924aa1e4e0.gif","duration":164.389,"title":"How Perpetual MCP Gives Agents Memory","description":"This Loom explains how Perpetual, an MCP running in your cloud, helps agents retain and reuse context via integrations rather than re-providing it each time. The speaker compares a setup with Perpetual and one without, showing that without the MCP there is no memory or access to required data, while with Perpetual the system connects to MongoDB Atlas to retrieve information. They demonstrate how new “skills” are created from prior chats and how updates, such as changing rules or tweaking numbers, can be written directly to MongoDB. The Loom also describes updating leadership-related information using prior conversations across tools like Linear and Slack."}