minimax_
1 MCP server offers this tool
What it usually takes
canvas– in 1 of 1duration– in 1 of 1enhance_prompt– in 1 of 1prompt– in 1 of 1reference_image– in 1 of 1sampler– in 1 of 1seed– in 1 of 1steps– in 1 of 1turbo_strength– 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? |
|---|---|---|
MiniMax-H3 Fused Turbo co.huggingface.hugging-apps/minimax-h3-fused-turbo-demo Reference-to-video: keep a subject's identity from a photo, in a new shot, with audio. This is the `ref2va` branch, which the fused ref-delta base exists for. Unlike image-to-video the reference is *not* the first frame — it is a labelled `<Picture 1>` the prompt refers to, and the model re-renders that subject in whatever the prompt describes. 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: The muxed MP4 and a markdown report of what actually ran. | canvas,duration,enhance_prompt,prompt,reference_image,sampler,seed,steps,turbo_strength | Not stated |