dayongd1/mcp-veo3
mcp-veo3 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-veo3 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.
The MCP Veo 3 Video Generation Server is a Model Context Protocol server that leverages Google's Veo 3 API through the Gemini API to provide advanced video generation capabilities.
Try mcp-veo3 with chat:
Tools
Functions exposed to the LLM to take actions
generate_video
Generate a video using Google Veo 3 from a text prompt
Args: prompt: Text prompt describing the video to generate model: Veo model to use (veo-3.0-generate-preview, veo-3.0-fast-generate-preview, veo-2.0-generate-001)
Returns: VideoGenerationResponse with video path, metadata, and generation info
Note: Veo 3 generates 8-second 720p videos with audio. Aspect ratio and other advanced parameters are not currently supported in the public API.
generate_video_from_image
Generate a video using Google Veo 3 from an image and text prompt
Args: prompt: Text prompt describing the video motion/action image_path: Path to the starting image file model: Veo model to use (veo-3.0-generate-preview, veo-3.0-fast-generate-preview, veo-2.0-generate-001)
Returns: VideoGenerationResponse with video path, metadata, and generation info
Note: Veo 3 generates 8-second 720p videos with audio. Advanced parameters like negative prompts and aspect ratios are not currently supported in the public API.
list_generated_videos
List all generated videos in the output directory
Returns: VideoListResponse with list of videos, count, and directory info
get_video_info
Get detailed information about a video file
Args: video_path: Path to the video file (can be relative to output directory)
Returns: VideoInfoResponse with file metadata
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client