videojev_35b_a3b_understand_video – 1 MCP server offers this tool
What it usually takes
context– in 1 of 1fps– in 1 of 1max_frames– in 1 of 1options– in 1 of 1query– in 1 of 1task– in 1 of 1threshold– in 1 of 1video– 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? |
|---|---|---|
VideoJev-35B-A3B co.huggingface.hugging-apps/videojev-35b-a3b Run VideoJev temporal grounding or multiple-choice video QA on a video. VideoJev is a System One model: a single forward pass scores candidate answers — it localizes a described moment in time or picks the correct option, without autoregressive decoding. 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: A markdown summary and a JSON payload with the grounding interval, in seconds (plus per-frame probabilities), or the chosen answer, (plus per-option probabilities). | context,fps,max_frames,options,query,task,threshold,video | Not stated |