Video Tools Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Video Tools Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An MCP server that gives Claude the ability to process videos: transcribe with Whisper, cut reels with FFmpeg, and manage video files.
| Tool | Description |
|---|---|
vt_transcribe | Transcribe video audio using OpenAI Whisper, saves timestamped .md |
vt_cut_reel | Cut a segment from a video using FFmpeg (fast seek + re-encode or stream copy) |
vt_rename | Rename video + transcript following a configurable naming convention |
vt_info | Get video metadata (duration, resolution, codec, fps, size) |
vt_list | List all videos in the working directory with transcript/cut status |
FFMPEG_PATH env var)git clone https://github.com/ZZtopBR/video-tools-mcp.git
cd video-tools-mcp
python3 -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt| Variable | Default | Description |
|---|---|---|
VT_VIDEOS_DIR | ~/videos | Working directory for videos |
FFMPEG_PATH | ffmpeg | Path to ffmpeg binary |
FFPROBE_PATH | ffprobe | Path to ffprobe binary |
VT_PREFIX | VT | Prefix for renamed files |
{
"mcpServers": {
"video-tools": {
"command": "/path/to/venv/bin/python",
"args": ["/path/to/video-tools-mcp/src/server.py"],
"env": {
"VT_VIDEOS_DIR": "/path/to/your/videos",
"FFMPEG_PATH": "ffmpeg"
}
}
}
}vt_transcribe generates a timestamped .md alongside the videovt_cut_reel extracts each segment as a separate filevt_rename applies consistent naming conventionsMIT
Built with [OpenAI Whisper](https://github.com/openai/whisper), [FFmpeg](https://ffmpeg.org), and [MCP](https://modelcontextprotocol.io) by Anthropic.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.