xiaomi_lens_0_grounded_answer – 1 MCP server offers this tool
What it usually takes
alpha– in 1 of 1draw_bbox– in 1 of 1image– in 1 of 1instruction– in 1 of 1mask_threshold– in 1 of 1max_new_tokens– in 1 of 1temperature– 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? |
|---|---|---|
Xiaomi-Lens-0 co.huggingface.seerray-lab/xiaomi-lens-0 Answer an instruction about an image and decode grounded regions into a mask overlay. The model streams its reasoning and answer as text; every final-answer <|mask|> token is decoded into a pixel segmentation mask that is composited onto the input image. 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 | alpha,draw_bbox,image,instruction,mask_threshold,max_new_tokens,temperature | Not stated |