dmad_generate – 1 MCP server offers this tool
What it usually takes
canvas– in 1 of 1prompt– in 1 of 1seed– 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? |
|---|---|---|
DMAD — 4-step MiniMax-H3 student co.huggingface.zhengmingyu/dmad Generate an audio-video clip (1344x768, ~5.2 s, 24 fps, stereo 32 kHz) from a text prompt. Runs the released 4-step DMAD student of MiniMax-H3 with the paper's re-noise sampler; seed 42 + the `lora_critic` checkpoint reproduces the repo's flagship `dmad_sweater` showcase video for its prompt. | canvas,prompt,seed | Not stated |