$ loading_
Analyze videos with frame extraction, scene detection, and metadata retrieval.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "mcp-video-vision" yet — see the docs or source repo.
Please analyze this video, extract one frame every 10 seconds, and list the key visuals in chronological order.
A time-ordered list of extracted frames with brief descriptions of each frame.
Please detect scene transition points in the video and summarize each scene with its start and end times.
A scene segmentation result with time ranges and a summary for each scene.
Please retrieve this video's metadata, including duration, resolution, frame rate, codec, and file size.
Structured video metadata suitable for asset inspection or downstream processing.
Extract video frames and metadata for LLM-powered video analysis workflows.
Analyze videos with scenes, transcripts, visual descriptions, and storyboards.
Analyze images and videos with configurable model providers for visual understanding.
Add private local image and video frame understanding to AI assistants.
Capture app or webpage screenshots and analyze them with a local vision model.
Analyze local or remote images with vision LLMs and generate descriptions.