REC 00:00:00;00
screencast-mcp Tools Workflows Connect GitHub ↗

SCREENCAST-MCP / TOOLS / EDIT

Redact Regions

redact_region

Cover given rectangles in a video (e.g. secrets on screen). Not automatic detection: find them with find_text redact: true. Off-frame regions are rejected.

editwritesdestructivesince v0.4.0

00:00PARAMETERS
NameTypeDescription
input requiredstringPath to the source video.
regions requiredobject[]Pixel rectangles (x, y, width, height), each optionally limited to start..end seconds. at least 1 items
regions[].x requiredinteger ≥ 0, ≤ 9007199254740991
regions[].y requiredinteger ≥ 0, ≤ 9007199254740991
regions[].width requiredinteger > 0, ≤ 9007199254740991
regions[].height requiredinteger > 0, ≤ 9007199254740991
regions[].startnumber ≥ 0
regions[].endnumber > 0
style"box" | "blur" | "pixelate"box (default): irreversible fill; blur/pixelate are partially recoverable.
padintegerGrow each region by this many px (default 0). ≥ 0, ≤ 9007199254740991
colorstringBox fill color (default black).
outputstringOptional output path. Defaults under SCREENCAST_HOME/edits.
overwritebooleanAllow replacing an existing file at the output path (default false).
00:05A MINIMAL CALL
redact_region { "input": "recording.mp4", "regions": [{"x": 0, "y": 0, "width": 1, "height": 1}] }

The required arguments only, with placeholder values. Everything else takes its default.

00:10WHAT COMES BACK

Structured content (structuredContent), alongside a text summary:

FieldTypeDescription
outputPath alwaysstringPath of the file written.
00:15SEEN IN