What it does
The server pulls scene frames from a video, each tagged with its timestamp, so an AI model can work with the visual content. It also applies OCR to the frames, which makes on-screen text available as well.
It suits workflows where an AI needs to read or review what appears in a video at specific points in time, rather than working from the audio or a transcript alone.
The publisher states that it runs on Apify and is charged per use.
Limitations and requirements
Runs on the Apify platform and is billed per use.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Errandkit Video Frames for AI
Extract timestamped scene frames from video for AI vision, with OCR. Runs on Apify, pay per use.
v1.0.0As shown on registry.modelcontextprotocol.io when we last read it