Skip to content
mcp/harbor
Grok

multimodal for Grok

io.github.rsmdt/multimodal

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

client:Grok transport:stdio runtime:npm

Install multimodal in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "multimodal": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@r16t/multimodal-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "XAI_API_KEY": "<XAI_API_KEY>",
        "GEMINI_API_KEY": "<GEMINI_API_KEY>",
        "ELEVENLABS_API_KEY": "<ELEVENLABS_API_KEY>",
        "BFL_API_KEY": "<BFL_API_KEY>",
        "MEDIA_OUTPUT_DIR": "<MEDIA_OUTPUT_DIR>"
      }
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

multimodal in other clients

multimodal MCP server