ace_brain_0_6_grounding_ground – 1 MCP server offers this tool
What it usually takes
add_format_instruction– in 1 of 1image– in 1 of 1max_new_tokens– in 1 of 1query– 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? |
|---|---|---|
ACE-Brain-0.6-9B Spatial Grounding co.huggingface.hugging-apps/ace-brain-0-6-grounding Ground a natural-language query in an image and draw the result. Given an image and a query such as "Point to the red cup", the model returns a point, a list of points, a bounding box, an integer count, or a categorical answer (yes / no / none), with coordinates as integers normalized to [0, 1000] along each image axis. Predicted points and boxes are drawn on the 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. Returns: (annotated image, parsed answer, raw model answer, prompt sent). | add_format_instruction,image,max_new_tokens,query | Not stated |