
Identify and clean AI watermarks and provenance in your own images, video, and text.
Public tool metadata for what this MCP can expose to an agent.
identifyReports which supported signals are present in an image or video, read-only.Reports which supported signals are present in an image or video, read-only.
No parameter schema in public metadata yet.
removeRemoves watermark signals from one image or video, writing a new output file beside the source unless an output path is given.Removes watermark signals from one image or video, writing a new output file beside the source unless an output path is given.
No parameter schema in public metadata yet.
batchProcesses a directory of images or videos, writing results to a separate output directory.Processes a directory of images or videos, writing results to a separate output directory.
No parameter schema in public metadata yet.
Sponsors
Remove AI provenance marks from images and video you generated yourself:
| Before | After |
|---|---|
![]() | ![]() |
uv tool install "remove-ai-watermarks[visible]" # CLI for visible marks and metadata
npx skills add wiltodelta/remove-ai-watermarks # agent skill for Claude Code, Codex, Cursor, and other agents
Video support covers provenance identification, complete visible-plus-metadata cleaning, directory batches, visible Sora, Veo, Seedance, Doubao, Dola, Hailuo AI, and Kling AI mark removal, and oracle-certified VAE regeneration for video SynthID removal.
remove-ai-watermarks