fast_vla_predict_robotwin – 1 MCP server offers this tool
What it usually takes
head– in 1 of 1head_t_minus_17– in 1 of 1head_t_minus_8– in 1 of 1instruction– in 1 of 1left_wrist– in 1 of 1memory_head– in 1 of 1memory_left_wrist– in 1 of 1memory_right_wrist– in 1 of 1right_wrist– in 1 of 1state– 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? |
|---|---|---|
Fast-VLA co.huggingface.hugging-apps/fast-vla Predict a 50-step bimanual action chunk (Aloha-AgileX, RoboTwin 2.0) with Fast-VLA. 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: Plot of the action chunk, table of actions (50 x 14), and a latency summary. | head,head_t_minus_17,head_t_minus_8,instruction,left_wrist,memory_head,memory_left_wrist,memory_right_wrist,right_wrist,state | Not stated |