MCP server for adding image watermarks and overlays to videos
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcpcn-video-image-watermark-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Video Image Watermark MCP A Model Context Protocol (MCP) server for adding image watermarks and overlays to videos. ## Features - **Image Overlay**: Add logos, watermarks, or any image to videos - Support for transparent PNG images - Customizable position, size, and opacity - Timed overlays with start/end time support - Automatic aspect ratio preservation ## Installation Install via uvx (recommended): ```bash uvx video-image-watermark-mcp ``` Or install via pip: ```bash pip install video-image-watermark-mcp ``` ## Usage Run the MCP server: ```bash video-image-watermark-mcp ``` ## Requirements - Python >=3.12 - FFmpeg installed on your system ## Tool ### `add_image_overlay` Add image overlay to video: - `video_path`: Input video file path - `output_video_path`: Output video file path - `image_path`: Overlay image path (supports transparent PNG) - `position`: Position preset ('top_left', 'top_right', 'bottom_left', 'bottom_right', 'center') or custom 'x=...:y=...' - `opacity`: Transparency (0.0-1.0) - `start_time`: When to start showing the overlay - `end_time`: When to stop showing the overlay - `width`: Target width (auto-calculates height if not specified) - `height`: Target height (auto-calculates width if not specified) ## License MIT License
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.