sahi_
1 MCP server offers this tool
What it usually takes
confidence_threshold– in 1 of 1image– in 1 of 1max_detections– in 1 of 1overlap_height_ratio– in 1 of 1overlap_width_ratio– in 1 of 1postprocess_class_agnostic– in 1 of 1postprocess_match_metric– in 1 of 1postprocess_match_threshold– in 1 of 1postprocess_type– in 1 of 1slice_height– in 1 of 1slice_width– in 1 of 1yolo_model_name– 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? |
|---|---|---|
Small Object Detection with YOLO11 co.huggingface.fcakyon/sahi-yolo11 Performs object detection using SAHI with a specified YOLOv11 model. 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: A tuple containing two PIL.Image.Image objects:, - The image with standard YOLO inference results., - The image with SAHI sliced YOLO inference results. | confidence_threshold,image,max_detections,overlap_height_ratio,overlap_width_ratio,postprocess_class_agnostic,postprocess_match_metric,postprocess_match_threshold,postprocess_type,slice_height,slice_width,yolo_model_name | Not stated |