MCP Server MCP

io.github.rsmdt/multimodal

By github 👁 1 views ▲ 0 votes

Multi-provider media generation — images, video, audio, and transcription via a unified interface

Homepage Verified source GitHub

Install

npx -y @r16t/[email protected]

Configuration Example

{
  "remotes": [],
  "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"
        }
      ]
    }
  ]
}

mcp model-context-protocol npm