MCP server for video content extraction: audio extraction, video trimming, frame extraction, and scene detection
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":"video-content-extractor-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 Content Extractor MCP A Model Context Protocol (MCP) server for video content extraction: audio extraction, video trimming, frame extraction, and scene detection. ## Features - **Audio Extraction**: Extract audio tracks from video files in various formats - **Video Trimming**: Cut video segments by time ranges with smart codec copying - **Frame Extraction**: Extract frames at intervals, first/last frames, or by scene changes - **Scene Detection**: Automatically detect scene changes and extract key frames ## Installation Install via uvx (recommended): ```bash uvx video-content-extractor-mcp ``` Or install via pip: ```bash pip install video-content-extractor-mcp ``` ## Usage Run the MCP server: ```bash video-content-extractor-mcp ``` ## Requirements - Python >=3.12 - FFmpeg installed on your system ## Tools Available 1. `extract_audio_from_video` - Extract audio tracks from video files 2. `trim_video` - Trim video segments by time range 3. `extract_video_frames` - Extract frames at intervals or specific positions 4. `extract_scene_change_frames` - Extract frames based on scene change detection ## 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.