scalereasoner_r1_pathology_predict – 1 MCP server offers this tool

What it usually takes

  • do_sample – in 1 of 1
  • high_mag_img – in 1 of 1
  • low_mag_img – in 1 of 1
  • max_new_tokens – in 1 of 1
  • mid_mag_img – in 1 of 1
  • option_a – in 1 of 1
  • option_b – in 1 of 1
  • option_c – in 1 of 1
  • option_d – in 1 of 1
  • question – in 1 of 1
  • temperature – in 1 of 1
  • top_p – 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

ServerInputsRead-only?
ScaleReasoner-R1 Pathology co.huggingface.hugging-apps/scalereasoner-r1-pathology Answer a cross-scale pathology multiple-choice question. Given three pathology images at different magnifications (10x low, 40x mid, 200x high) and a multiple-choice question with four options, produces a structured reasoning trace and the single best answer letter. 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: A tuple of (answer_letter, reasoning_text, full_response).do_sample,high_mag_img,low_mag_img,max_new_tokens,mid_mag_img,option_a,option_b,option_c,option_d,question,temperature,top_pNot stated