fast_vla_predict_libero – 1 MCP server offers this tool
What it usually takes
agentview– in 1 of 1instruction– in 1 of 1memory_agentview– in 1 of 1memory_wrist– in 1 of 1state– in 1 of 1upright_input– in 1 of 1wrist– 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 10-step Franka end-effector action chunk (LIBERO) 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 (10 x 7), and a latency summary. | agentview,instruction,memory_agentview,memory_wrist,state,upright_input,wrist | Not stated |