imagine mcp for VS Code

io.github.n24q02m/imagine-mcp

MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)

client:VS Code transport:stdio runtime:pypi

Install imagine mcp in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "understand-models",
      "description": "UNDERSTAND_MODELS",
      "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": "xai-api-key",
      "description": "XAI_API_KEY",
      "password": true
    }
  ],
  "servers": {
    "imagine-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "imagine-mcp"
      ],
      "env": {
        "UNDERSTAND_MODELS": "${input:understand-models}",
        "GEMINI_API_KEY": "${input:gemini-api-key}",
        "OPENAI_API_KEY": "${input:openai-api-key}",
        "XAI_API_KEY": "${input:xai-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

imagine mcp in other clients

imagine mcp MCP server