dexmal_dm05_vla_predict – 1 MCP server offers this tool
What it usually takes
control_mode– in 1 of 1diffusion_steps– in 1 of 1image_head– in 1 of 1image_left_wrist– in 1 of 1image_right_wrist– in 1 of 1instruction– in 1 of 1speed– in 1 of 1state_text– 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? |
|---|---|---|
DM0.5 Vision-Language-Action co.huggingface.hugging-apps/dexmal-dm05-vla Predict a bimanual robot action trajectory from cameras + an instruction. 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 trajectory plot (image) and the raw predicted action array as JSON text. | control_mode,diffusion_steps,image_head,image_left_wrist,image_right_wrist,instruction,speed,state_text | Not stated |