facial_
1 MCP server offers this tool
What it usually takes
image– in 1 of 1model_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? |
|---|---|---|
Facial Keypoint Detection co.huggingface.konihd/facial-keypoint-detection Run facial keypoint detection on a face image and return the annotated result. Returns: tuple: (keypoint_image, info_string) where keypoint_image is the face annotated, with 68 predicted landmarks, and info_string describes the model and output. | image,model_name | Not stated |