Skip to content

Video Understanding MCP for Grok

io.github.granitebps/video-understanding-mcp

Let AI agents watch videos and answer questions about them through any OpenAI-compatible endpoint.

client:Grok transport:stdio runtime:npm

Install Video Understanding MCP 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": {
    "video-understanding-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@granitebps/video-understanding-mcp"
      ],
      "env": {
        "VIDEO_BASE_URL": "<VIDEO_BASE_URL>",
        "VIDEO_MODEL": "<VIDEO_MODEL>",
        "VIDEO_API_KEY": "<VIDEO_API_KEY>",
        "VIDEO_EXTRA_HEADERS": "<VIDEO_EXTRA_HEADERS>",
        "VIDEO_PART_FORMAT": "<VIDEO_PART_FORMAT>",
        "VIDEO_MAX_DURATION_SECONDS": "<VIDEO_MAX_DURATION_SECONDS>",
        "VIDEO_MAX_UPLOAD_MB": "<VIDEO_MAX_UPLOAD_MB>",
        "VIDEO_ALLOWED_DIRS": "<VIDEO_ALLOWED_DIRS>",
        "VIDEO_VERIFY_MEDIA": "<VIDEO_VERIFY_MEDIA>"
      }
    }
  }
}

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

Video Understanding MCP in other clients