multimodal

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.rsmdt/multimodal",
  "description": "Multi-provider media generation — images, video, audio, and transcription via a unified interface",
  "repository": {
    "url": "https://github.com/rsmdt/multimodal-mcp",
    "source": "github"
  },
  "version": "1.3.1",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@r16t/multimodal-mcp",
      "version": "1.3.1",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "OpenAI API key for image, video, audio generation and transcription",
          "format": "string",
          "isSecret": true,
          "name": "OPENAI_API_KEY"
        },
        {
          "description": "xAI API key for image and video generation",
          "format": "string",
          "isSecret": true,
          "name": "XAI_API_KEY"
        },
        {
          "description": "Google Gemini API key for image, video, and audio generation",
          "format": "string",
          "isSecret": true,
          "name": "GEMINI_API_KEY"
        },
        {
          "description": "ElevenLabs API key for audio generation and transcription",
          "format": "string",
          "isSecret": true,
          "name": "ELEVENLABS_API_KEY"
        },
        {
          "description": "BFL API key for FLUX image generation and editing",
          "format": "string",
          "isSecret": true,
          "name": "BFL_API_KEY"
        },
        {
          "description": "Directory for saved media files (defaults to cwd)",
          "format": "string",
          "name": "MEDIA_OUTPUT_DIR"
        }
      ]
    }
  ]
}