diffusiongemma_radiology_vqa_infill_report – 1 MCP server offers this tool
What it usually takes
adapter_label– in 1 of 1bidirectional– in 1 of 1image– in 1 of 1max_new_tokens– in 1 of 1template– 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? |
|---|---|---|
DiffusionGemma Radiology VQA co.huggingface.hugging-apps/diffusiongemma-radiology-vqa Fill a [BLANK] span in a partial radiology report using the diffusion canvas. The known text becomes fixed canvas positions; the [BLANK] span is denoised. With `bidirectional=True` the model sees text on both sides of the hole; with it False, only the left context is kept (the autoregressive-style baseline). 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: Just the text the model wrote into the [BLANK]. | adapter_label,bidirectional,image,max_new_tokens,template | Not stated |