Generate videos from text prompts or images using Google's Veo2 model via a Model Context Protocol (MCP) server.
This project implements a Model Context Protocol (MCP) server, enabling video generation through Google's Veo2 model. It allows users to create videos from text or image inputs, providing access to these generated videos through MCP resources. With support for stdio and SSE transports, and example video generation templates, it provides a streamlined interface for leveraging AI-powered video creation.