gemini mcp for VS Code

io.github.chrischall/gemini-mcp

Generate and edit images with Google Gemini (Nano Banana / Nano Banana Pro) image models.

client:VS Code transport:stdio runtime:npm

Install gemini mcp in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "gemini-api-key",
      "description": "GEMINI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "gemini-image-model",
      "description": "GEMINI_IMAGE_MODEL",
      "password": true
    },
    {
      "type": "promptString",
      "id": "gemini-output-dir",
      "description": "GEMINI_OUTPUT_DIR",
      "password": true
    },
    {
      "type": "promptString",
      "id": "gemini-input-dir",
      "description": "GEMINI_INPUT_DIR",
      "password": true
    }
  ],
  "servers": {
    "gemini-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@chrischall/gemini-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "${input:gemini-api-key}",
        "GEMINI_IMAGE_MODEL": "${input:gemini-image-model}",
        "GEMINI_OUTPUT_DIR": "${input:gemini-output-dir}",
        "GEMINI_INPUT_DIR": "${input:gemini-input-dir}"
      }
    }
  }
}

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

gemini mcp in other clients

gemini mcp MCP server