video vision mcp for VS Code

io.github.kitdevua/video-vision-mcp

Analyze any video (local file or URL) into frames + transcript for Claude Code

client:VS Code transport:stdio runtime:pypi

Install video vision mcp in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "video-mcp-env",
      "description": "VIDEO_MCP_ENV",
      "password": true
    },
    {
      "type": "promptString",
      "id": "gemini-api-key",
      "description": "GEMINI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "openai-api-key",
      "description": "OPENAI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "groq-api-key",
      "description": "GROQ_API_KEY",
      "password": true
    }
  ],
  "servers": {
    "video-vision-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "video-vision-mcp"
      ],
      "env": {
        "VIDEO_MCP_ENV": "${input:video-mcp-env}",
        "GEMINI_API_KEY": "${input:gemini-api-key}",
        "OPENAI_API_KEY": "${input:openai-api-key}",
        "GROQ_API_KEY": "${input:groq-api-key}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

video vision mcp in other clients

video vision mcp MCP server