ervla_predict – 1 MCP server offers this tool
What it usually takes
base_view– in 1 of 1chunk_length– in 1 of 1instruction– in 1 of 1robot_type– in 1 of 1seed– in 1 of 1state_aa1– in 1 of 1state_aa2– in 1 of 1state_aa3– in 1 of 1state_ee_x– in 1 of 1state_ee_y– in 1 of 1state_ee_z– in 1 of 1state_finger_l– 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? |
|---|---|---|
ERVLA co.huggingface.hugging-apps/ervla Predict a LIBERO end-effector action chunk from two camera views + 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: (plotly figure of the Δx/Δy/Δz deltas, chunk table, CSV text, status line). | base_view,chunk_length,instruction,robot_type,seed,state_aa1,state_aa2,state_aa3,state_ee_x,state_ee_y,state_ee_z,state_finger_l,state_finger_r,wrist_view | Not stated |