fara_computer_use_27b_predict_action – 1 MCP server offers this tool
What it usually takes
max_new_tokens– in 1 of 1screenshot– in 1 of 1task– 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? |
|---|---|---|
Fara-1.5-27B Computer-Use Agent co.huggingface.hugging-apps/fara-computer-use-27b Predict the next browser action a computer-use agent should take. Given a browser screenshot and a natural-language task, Microsoft's Fara-1.5-27B computer-use agent returns its chain-of-thought reasoning and a structured `computer_use` tool call (click coordinates, typing, navigation, etc.). Click/move targets are drawn on the 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: annotated_image, raw_model_output, parsed_action_summary | max_new_tokens,screenshot,task | Not stated |