
Video Understanding MCP
Let AI agents watch videos and answer questions about them through any OpenAI-compatible endpoint.
- tools
- 2
- auth
- Secret needed
- transport
- STDIO
- env vars
- 8
- last updated
- Nov 9, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
understand_videoWatch a video from a page URL, direct media URL, or local path and answer a question about it, returning a structured answer.
Watch a video from a page URL, direct media URL, or local path and answer a question about it, returning a structured answer.
No parameter schema in public metadata yet.
get_server_infoShows the version, endpoint host and model, request format, limits, local-file policy, and whether ffmpeg, ffprobe, and yt-dlp are available.
Shows the version, endpoint host and model, request format, limits, local-file policy, and whether ffmpeg, ffprobe, and yt-dlp are available.
No parameter schema in public metadata yet.
Sponsors
Configuration
VIDEO_BASE_URL*Base URL of an OpenAI-compatible chat completions endpoint whose model accepts video, e.g. https://host/v1
VIDEO_MODEL*Model (or router alias) to send videos to
VIDEO_API_KEYsecretEndpoint API key, sent as a bearer token
VIDEO_PART_FORMATdefault: image_urlHow the video is attached: video_url, image_url, file, or input_file
VIDEO_MAX_DURATION_SECONDSdefault: 300Longest analyzed range in seconds
VIDEO_MAX_UPLOAD_MBdefault: 15Largest prepared video sent to the endpoint, in MB
VIDEO_ALLOWED_DIRSDirectories local files may be read from; local files are refused when unset
VIDEO_VERIFY_MEDIAdefault: trueFail calls when the endpoint evidently ignored the video
Readme
Video Understanding MCP
An MCP server that lets AI agents watch a video and answer questions about it: what is shown, what is said, what text appears on screen, and when. It works with any OpenAI-compatible chat completions endpoint whose model accepts video, such as Gemini models served through a gateway.
Give it a TikTok, YouTube, or X post URL, a direct media URL from a scraper, or a local file, plus a question. It downloads and shrinks the video, sends it to your endpoint, and returns a structured answer:
Details
- Repository
- github.com/granitebps/video-understanding-mcp
- Categories
- AI & LLM Tools, Media & Entertainment
- Package
@granitebps/video-understanding-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active