mcp-video
Verified Safeby VMRam95
Overview
Enables LLMs to analyze video content by extracting frames as images and, in the future, transcribing audio to text.
Installation
node dist/index.jsEnvironment Variables
- VIDEO_BASE_DIR
- OPENAI_API_KEY
- TRANSCRIPTION_BACKEND
- WHISPER_MODEL
- CACHE_ENABLED
- CACHE_DIR
- MAX_FRAMES_DEFAULT
- FRAME_QUALITY_DEFAULT
- FFMPEG_PATH
- FFPROBE_PATH
Security Notes
The server relies heavily on `ffmpeg` and `ffprobe` binaries, invoked via `child_process.spawn`. While path validation (`normalizePath`, `validateVideoPath`) is implemented to mitigate directory traversal in tool inputs, the inherent risk of spawning external processes exists. The web server's file upload (`src/web/server.ts`, `parseMultipart`) lacks explicit size limits, posing a potential denial-of-service vulnerability by allowing large file uploads to fill disk space. No apparent hardcoded secrets or obfuscation were found. The `OPENAI_API_KEY` is expected to be an environment variable for future transcription features.
Similar Servers
yt-dlp-mcp
Integrate video platform capabilities like search, metadata extraction, and content download into AI agents using yt-dlp.
cloudglue-mcp-server
Connects Cloudglue to AI assistants for video collection understanding, enabling LLMs to analyze videos, extract structured data, and gain insights from visual and audio content.
youtube-transcript-mcp
Enables LLM chat applications to summarize or analyze content from YouTube videos by providing their transcripts.
pdf4vllm-mcp
PDF content extraction and search, optimized for messy documents and vision language models (LLMs), with features for text corruption detection, reading order preservation, and token management.