mario-andreschak/mcp-veo2
mcp-veo2 is hosted online, so all tools can be tested directly either in theInspector tabor in theOnline Client.
If you are the rightful owner of mcp-veo2 and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
This project implements a Model Context Protocol (MCP) server that exposes Google's Veo2 video generation capabilities, allowing clients to generate videos from text prompts or images.
Try mcp-veo2 with chat:
Tools
Functions exposed to the LLM to take actions
generateVideoFromText
Generate a video from a text prompt
generateVideoFromImage
Generate a video from an image
generateImage
Generate an image from a text prompt using Google Imagen
generateVideoFromGeneratedImage
Generate a video from a generated image (one-step process)
listGeneratedVideos
List all generated videos
getImage
Get a specific image by ID
listGeneratedImages
List all generated images
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client
video-templates
URI: videos://templates
MIME: text/plain
Example prompts for generating videos with Veo2
image-templates
URI: images://templates
MIME: text/plain
Example prompts for generating images with Google Imagen
Image: Respectful, brand-safe 16:9 illustration: candlelight vigil outside a stone Catholic church at dusk. Silhouetted community members comforting each other, soft warm candlelight, blurred emergency vehicle lights in background, no visible faces, calm somber color palette, hopeful but solemn tone.
URI: images://870a3cd4-d61f-4166-a4ea-14e585e6d167
MIME: image/png
Access generated images
