Clipto MCP gives Claude, ChatGPT, and other AI agents the ability to source clips and more from inside the videos, photos, and audio recordings stored on your computer.
Instead of manually browsing files, simply describe what you need. For example, turn a script into a video by matching each sentence with your local footage; find every scene where someone mentioned a topic; create rough cuts; or search years of media as if you have a dedicated assistant editor.
Like Google Photos, but fully local. Turn the terabytes of video, audio, meetings, and files you work with into searchable memories, without uploading anything to the cloud. Clipto automatically tags people, dialogue, and scenes, so you can instantly find any moment buried in your media just by describing what you're looking for. It's fast too: on a MacBook Pro M5, Clipto indexed 2TB of videos in just 24 hours.
I've been thinking about this after seeing Clipto.ai.
We re surrounded by content now videos, podcasts, articles, posts, tutorials and tools are getting really good at helping us save and summarize all of it.
But I wonder if there's another problem underneath:
What happens to all the useful things we save but never come back to?
One of the experiments we tried while building Clipto MCP ended up being way more fun than expected.
We had indexed around 1,000 clips from Elon Musk interviews in Clipto. Instead of giving Claude a specific editing task, we basically asked: What would be something fun to make with all this footage?
