Gemini Media MCP
A unified Go MCP server enabling AI media generation via Google Gemini API and Vertex AI. It supports generating images, video, speech, and music. Features include cost-awareness with budget caps, agent-friendly error handling, async video jobs with progress notifications, and built-in skills for workflows like upscaling and multi-asset production.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Generate images using Nano Banana or Pro models
- Create video clips with Veo 3.1 or Gemini Omni Flash
- Synthesize speech using Gemini 3.8 TTS
- Generate music tracks using Lyria 3.5
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/mordor-forge/gemini-media-mcp/releases/download/v1.1.0/gemini-media-mcp-1.1.0.mcpb 1.1.0
{
"version": "1.1.0",
"transport": "stdio",
"fileSha256": "a23aac14b81d76f8bc3dd1b18867a7c8d206908143716a4e1073928f2eea8c0f",
"identifier": "https://github.com/mordor-forge/gemini-media-mcp/releases/download/v1.1.0/gemini-media-mcp-1.1.0.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like Gemini Media MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.