mcp-veo2
MCP for Video- or Image-Generation with Google VEO2
claude mcp add --transport stdio mario-andreschak-mcp-veo2 node dist/server.js \ --env PORT="3000" \ --env LOG_LEVEL="fatal" \ --env STORAGE_DIR="./generated-videos" \ --env GOOGLE_API_KEY="Your Google API key"
How to use
This MCP server exposes Google's Veo2 video generation capabilities via the MCP protocol. It lets clients generate videos from text prompts or from input images, then access the produced videos through MCP resources. The server supports both stdio and SSE transports for MCP communication and can be run in environments where Node.js is available. After starting the server, you can use the provided MCP tools to create new videos, list existing ones, and retrieve templates.
Key capabilities include: generateVideoFromText for creating videos from descriptive prompts, generateVideoFromImage for image-guided video generation, and listGeneratedVideos to enumerate available outputs. Each tool accepts a structured payload with options like aspect ratio, duration, and safety/generation constraints. Generated videos are exposed as MCP resources under videos://{id} and there is a templates resource at videos://templates for example configurations.
How to install
Prerequisites:
- Node.js 18 or higher
- npm (comes with Node.js)
- Git
Installation steps:
- Clone the repository
git clone https://github.com/yourusername/mcp-video-generation-veo2.git
cd mcp-video-generation-veo2
- Install dependencies
npm install
- Create and configure environment file
cp .env.example .env
Edit .env to include your Google API key and adjust options as needed:
- GOOGLE_API_KEY: Your Google API key
- PORT: Server port (default 3000)
- STORAGE_DIR: Directory to store generated videos (default ./generated-videos)
- LOG_LEVEL: Logging level (default fatal)
- Build the project
npm run build
- Run the server (stdio transport by default)
npm start
To run with SSE transport, use:
npm start sse
Additional notes
Environment variables can significantly impact runtime behavior. Ensure GOOGLE_API_KEY has access to the Veo2 API. If you experience missing assets or failed requests, verify that the STORAGE_DIR exists and is writable. The LOG_LEVEL can be increased to debug/info during development to troubleshoot prompts, image inputs, or template loading. When deploying, consider setting PORT via environment rather than relying on the default. If you plan to expose the MCP server publicly, implement appropriate authentication and rate limiting at the network level.
Common issues:
- Missing GOOGLE_API_KEY: Ensure the key is set and valid.
- Port already in use: Change PORT or stop the conflicting service.
- Build failures: Check Node.js version compatibility and dependencies.
MCP Resources:
- videos://{id} to access a generated video
- videos://templates for example templates
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
mcp-google-map
A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)