SSyncDev

Video Understanding MCP Server

Let AI agents watch videos and answer questions about them through any OpenAI-compatible endpoint.

Local serverstdio

What is the Video Understanding MCP Server?

Video Understanding MCP is an MCP integration. Let AI agents watch videos and answer questions about them through any OpenAI-compatible endpoint.

Packages and local setup

The published npm package is @granitebps/video-understanding-mcp, version 1.0.2. Its declared MCP transport is stdio.

The package declares VIDEO_BASE_URL (required): Base URL of an OpenAI-compatible chat completions endpoint whose model accepts video, e.g. https://host/v1; VIDEO_MODEL (required): Model (or router alias) to send videos to; VIDEO_API_KEY: Endpoint API key, sent as a bearer token; VIDEO_EXTRA_HEADERS: Extra endpoint request headers as a JSON object, such as Cloudflare Access service-token headers; VIDEO_PART_FORMAT: How the video is attached: video_url, image_url, file, or input_file; VIDEO_MAX_DURATION_SECONDS: Longest analyzed range in seconds; VIDEO_MAX_UPLOAD_MB: Largest prepared video sent to the endpoint, in MB; VIDEO_ALLOWED_DIRS: Directories local files may be read from; local files are refused when unset; VIDEO_VERIFY_MEDIA: Fail calls when the endpoint evidently ignored the video.

Before connecting

Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.

Project and source

View the publisher’s registry entry · Project repository. This profile uses version 1.0.2 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.

Browse related ai & ml services MCP servers for tools that cover the same kind of work.

Configuration

VariableDescriptionRequired
VIDEO_BASE_URLBase URL of an OpenAI-compatible chat completions endpoint whose model accepts video, e.g. https://host/v1Yes
VIDEO_MODELModel (or router alias) to send videos toYes
VIDEO_API_KEYEndpoint API key, sent as a bearer tokenCheck documentation
VIDEO_EXTRA_HEADERSExtra endpoint request headers as a JSON object, such as Cloudflare Access service-token headersCheck documentation
VIDEO_PART_FORMATHow the video is attached: video_url, image_url, file, or input_fileCheck documentation
VIDEO_MAX_DURATION_SECONDSLongest analyzed range in secondsCheck documentation
VIDEO_MAX_UPLOAD_MBLargest prepared video sent to the endpoint, in MBCheck documentation
VIDEO_ALLOWED_DIRSDirectories local files may be read from; local files are refused when unsetCheck documentation
VIDEO_VERIFY_MEDIAFail calls when the endpoint evidently ignored the videoCheck documentation