mordor-forge/gemini-media

v1.0.0Apache-2.0

Generate images (Nano Banana), video (Veo, Gemini Omni), speech (Gemini TTS) and music (Lyria) with Google's generative media models, with cost estimates and spend budgets.

GitHub Open Website

MCP servers

Declared configuration, as published in mcp.json. The directory shows indexed content; it never connects to or executes these servers.

gemini-mediastdio

{
  "type": "stdio",
  "command": "gemini-media-mcp",
  "args": []
}

What this package declares

The files a client reads when it loads this plugin, exactly as this revision carries them.

{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "gemini-media",
  "version": "1.0.0",
  "description": "Generate images (Nano Banana), video (Veo, Gemini Omni), speech (Gemini TTS) and music (Lyria) with Google's generative media models, with cost estimates and spend budgets.",
  "author": {
    "name": "mordor-forge",
    "url": "https://github.com/mordor-forge"
  },
  "homepage": "https://github.com/mordor-forge/gemini-media-mcp#readme",
  "repository": "https://github.com/mordor-forge/gemini-media-mcp",
  "license": "Apache-2.0",
  "keywords": [
    "mcp",
    "gemini",
    "nano-banana",
    "veo",
    "lyria",
    "text-to-speech",
    "image-generation",
    "video-generation",
    "music-generation"
  ],
  "extensions": {
    "com.openai": {
      "interface": {
        "displayName": "Gemini Media",
        "shortDescription": "Create images, video, speech and music with Google's Gemini media models",
        "longDescription": "Adds the gemini-media MCP server and skills for Nano Banana images, Veo and Gemini Omni video, Gemini text-to-speech and Lyria music. Every generation reports its estimated cost, and optional budgets stop runaway spend. Needs the gemini-media-mcp binary on your PATH (see the README) and a Gemini API key or a Vertex AI project: run `gemini-media-mcp configure --api-key-stdin` once, or export GEMINI_API_KEY.",
        "developerName": "mordor-forge",
        "category": "Design",
        "capabilities": [
          "Read",
          "Write"
        ],
        "websiteURL": "https://github.com/mordor-forge/gemini-media-mcp",
        "privacyPolicyURL": "https://policies.google.com/privacy",
        "termsOfServiceURL": "https://ai.google.dev/gemini-api/terms",
        "defaultPrompt": [
          "Generate a 16:9 hero image of a lighthouse at dusk",
          "Estimate what an 8-second 1080p Veo clip would cost",
          "Turn this paragraph into a two-voice podcast intro"
        ]
      }
    }
  }
}

What else this package ships

These files come with the package and this site does not publish them. They are listed so you know what is there before you install it.

10JSON files
onboarding_it.txt
LICENSE

View on GitHub

Client extensions

Data this package carries for particular clients. The directory lists the clients named and never reads what is addressed to them.

com.openai