worldguide_
1 MCP server offers this tool
What it usually takes
category– in 1 of 1flow_shift– in 1 of 1guidance_scale– in 1 of 1num_inference_steps– in 1 of 1override_action– in 1 of 1seed– in 1 of 1start_image– in 1 of 1subject– in 1 of 1video_length– 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? |
|---|---|---|
WorldGuide co.huggingface.hugging-apps/worldguide Run one closed-loop WorldGuide step: the ContextPlanner looks at the current state and predicts the next atomic action, then the video DiT executes it as a short clip. 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: Latest step clip, full stitched rollout video, step log (markdown) and the updated state. | category,flow_shift,guidance_scale,num_inference_steps,override_action,seed,start_image,subject,video_length | Not stated |