gemini-media-mcp
Unified Go MCP server for AI media generation via Google Gemini API and Vertex AI.
Features
- Image generation -- text-to-image with configurable aspect ratios and resolutions (1K/2K/4K)
- Image editing -- modify existing images with natural language prompts
- Multi-reference composition -- combine up to 3 reference images with style/content guidance
- Video generation -- text-to-video via Veo 3.1 Lite, Fast, and Standard tiers
- Image-to-video -- animate still images into video clips
- Video extension -- chain clips for longer content (Fast and Standard tiers)
- Text-to-speech -- generate spoken audio with configurable voices and languages
- Music generation -- AI music via Lyria 3 (30s clips or full songs with vocals, structure control)
- Single binary -- no runtime dependencies, runs over stdio transport
- Provider abstraction -- backend-agnostic interfaces for image, video, audio, and model operations
- Dual backend -- supports both Gemini API (API key) and Vertex AI (project credentials)
