wan_studio_pro_v2_scene_step_7 – 1 MCP server offers this tool
What it usually takes
name_hint– in 1 of 1param_10– in 1 of 1param_11– in 1 of 1param_12– in 1 of 1param_13– in 1 of 1param_14– in 1 of 1param_15– in 1 of 1param_16– in 1 of 1param_17– in 1 of 1param_18– in 1 of 1param_19– in 1 of 1param_20– 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? |
|---|---|---|
Wan 2.2 I2V 14B Pro v2 co.huggingface.vml12/wan-studio-pro-v2 One clip of a chain, and nothing at all once the chain is finished. Deliberately one clip per call rather than a loop inside a single handler. A ZeroGPU token is minted for the browser request that started the work and it expires within minutes; a loop that runs for a quarter of an hour is still holding the first one by clip two. Chaining separate steps means every clip arrives on its own fresh request. The start image is handed back as the last frame of the clip just made, so the next step picks it up without anything having to be threaded through. 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 | name_hint,param_10,param_11,param_12,param_13,param_14,param_15,param_16,param_17,param_18,param_19,param_20,param_21,param_22,param_23,param_24,param_25,param_26,param_27,param_28,param_29,param_30,param_31,param_32,param_33,param_34,param_35,param_36,param_37,param_38,param_39,param_40,param_41,param_42,param_43,param_44,param_45,param_46,param_47,param_48,param_49,param_50,param_51,param_52,param_53,param_54,param_55,param_56,param_57,param_58,param_59,param_60,param_61,param_62,param_63,param_64,param_65,scene_prompts,sound_engine,sound_guidance,sound_negative,sound_on,sound_prompt,sound_steps | Not stated |