Wan_2_2_I2V_Studio_2_stage_extension – 1 MCP server offers this tool
What it usually takes
current_image– in 1 of 1identity_ref– in 1 of 1name_hint– in 1 of 1video_path– 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 Studio · AI Scene Planner co.huggingface.ben2390/wan_2.2_i2v_studio-2 Before a continuation runs: park the finished clip in the merge queue and hand its last frame back as the new starting image. The clip is always parked, whatever the auto-merge box says - otherwise the first clip of a chain is lost and the stitched file starts from the second one. The end frame is wiped as well: an end frame left over from the previous take drags every continuation back to the same picture. The identity lock is only ever the face the user uploaded, so the new clip opens on exactly the frame the old one closed on and the seam trims cleanly. 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 | current_image,identity_ref,name_hint,video_path | Not stated |