dk_ vlm_ answer
1 MCP server offers this tool
What it usually takes
geo_weight– in 1 of 1max_new_tokens– in 1 of 1nframes– in 1 of 1options_text– in 1 of 1question– 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? |
|---|---|---|
DK-VLM — Geometry as Position co.huggingface.hugging-apps/dk-vlm Answer a spatial question about a scene video with the DK-VLM pipeline. 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: (answer, geometry coverage, timing breakdown) | geo_weight,max_new_tokens,nframes,options_text,question,video | Not stated |