Gemini Veo MCP
Provides tools for generating videos using Google Gemini Veo based on text prompts.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Gemini Veo MCPgenerate a video of a cat playing piano"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Gemini Veo MCP
A simple Model Context Protocol (MCP) server for generating videos using Google Gemini Veo.
Setup
Install Dependencies:
npm installConfigure API Key: Update the
.envfile with your Google Gemini API Key:GEMINI_API_KEY=your_actual_key_hereBuild:
npx tsc
Related MCP server: Gemini Image Generation MCP Server
Using with Claude Code
Option 1: Claude CLI (Recommended)
Run this command to add the MCP server automatically to your configuration:
claude mcp add gemini-veo --scope user -- node /Users/iser/workspace/gemini-veo-mcp/dist/index.jsOption 2: Manual Config
Add this to your Claude config (~/.claude.json):
{
"mcpServers": {
"gemini-veo": {
"command": "node",
"args": ["/Users/iser/workspace/gemini-veo-mcp/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your_actual_key_here"
}
}
}
}Or run Claude with the MCP enabled:
claude --mcp gemini-veo:node:/Users/iser/workspace/gemini-veo-mcp/dist/index.jsTools
generate_video
Generates a video based on a text prompt.
prompt: (string) Description of the video.aspect_ratio: (string, optional) "16:9", "9:16", or "1:1".
This server cannot be deployed
Maintenance
Related MCP Connectors
Create images and videos from prompts, with options for image mixing, reference images, and start/…
Generate images, videos, voiceovers, and captions from a chat prompt.
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
Generate video, images, audio and speech with Vidofy — Veo 3.1, Kling 3.0, Flux 2 and 570+ models.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables video generation from text prompts or images using Google's Veo 3 API. Supports multiple models, audio generation, and various aspect ratios for creating high-quality videos.3MIT
- AlicenseNot gradedqualityNot gradedmaintenanceEnables image generation using Google's Gemini 2 API with customizable parameters like aspect ratio, number of samples, and person generation settings.65 npm-
- AlicenseNot gradedqualityBmaintenanceGenerates images from text prompts using Google's Gemini AI models with customizable aspect ratios and resolutions up to 4K, automatically saving images locally.37 npm2MIT
- FlicenseAqualityDmaintenanceEnables high-quality AI video generation using Google's Veo 3.1 model for text-to-video, style-guided, and frame-interpolation tasks. It features token-efficient reference image handling, batch processing, and video extension capabilities with built-in cost estimation.62-