Sa2VA_
1 MCP server offers this tool
What it usually takes
prompt– in 1 of 1video_input_path– in 1 of 1video_interval– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
Sa2VA Simple Demo co.huggingface.fffiloni/sa2va-simple-demo Perform video-based visual question answering and segmentation. This function analyzes a video file using a multimodal vision-language model. It extracts frames based on a sampling interval, feeds the frames and prompt to the model, and returns a response. If segmentation is requested, it produces two videos: one with overlaid masks, and one with binary masks only. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: Tuple[str, Optional[str], Optional[str]]:, - The model-generated textual answer., - If segmentation is requested (contains '[SEG]'), the path to the segmented output video file., - If segmentation is requested, the path to a binary mask-only video; otherwise, None. | prompt,video_input_path,video_interval | Not stated |