Redact Regions
redact_regionCover specified rectangular regions in videos or screenshots to hide secrets and sensitive on-screen content. Provide pixel coordinates; out-of-frame regions are rejected.
Instructions
Cover given rectangles in a video or screenshot (e.g. secrets on screen). Not automatic detection: find them with find_text redact: true. Off-frame regions are rejected.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"input": "<input>",
"regions": "<regions>"
},
"name": "redact_region"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| pad | No | Grow each region by this many px (default 0). | |
| color | No | Box fill color (default black). | |
| input | Yes | Path to the source video or image (png/jpg; time ranges are ignored for an image). | |
| style | No | box (default): irreversible fill; blur/pixelate are partially recoverable. | |
| output | No | Optional output path. Defaults under SCREENCAST_HOME/edits. | |
| regions | Yes | Pixel rectangles (x, y, width, height), each optionally limited to start..end seconds. | |
| overwrite | No | Allow replacing an existing file at the output path (default false). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| outputPath | Yes | Path of the file written. |