mnistvit_predict_base64 – 1 MCP server offers this tool
What it usually takes
image_base64– in 1 of 1return_probs– 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? |
|---|---|---|
mnistvit MNIST Vision Transformer co.huggingface.asnelt/mnistvit Predict a digit from an inline base64-encoded image, with no file hosting required. Uses mnistvit, a vision transformer (ViT) trained on MNIST with 99.65% test accuracy to classify the image. This is the MCP-friendly entry point: unlike `predict_file`, which needs a URL, this endpoint accepts the raw image bytes as a base64 string directly in the request. The model classifies at 28 x 28 pixels internally, so there is no accuracy benefit to calling with a larger image. Returns: int or dict: Predicted digit class label or dict of digit class probabilities., Raises:, gradio.Error: If the image is not provided or malformed. | image_base64,return_probs | Not stated |