llada_ui_gui_agent_demo_act – 1 MCP server offers this tool
What it usually takes
block_length– in 1 of 1gen_length– in 1 of 1image– in 1 of 1platform– in 1 of 1previous_action– in 1 of 1steps– in 1 of 1task– in 1 of 1temperature– in 1 of 1threshold– 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? |
|---|---|---|
LLaDA-UI co.huggingface.inclusionai/llada-ui-gui-agent-demo Predict the next GUI action for a task, given the current screenshot. 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: The screenshot with any predicted coordinate marked, the parsed action, the, model's reasoning, and the raw output. | block_length,gen_length,image,platform,previous_action,steps,task,temperature,threshold | Not stated |