Gemini Pro MCP for VS Code

io.github.muzaqil555/gemini-pro-mcp

Your Google AI Pro plan in Claude, Codex and Gemini CLI: Gemini, Flow, Notebooks, Jules, Veo

client:VS Code transport:stdio runtime:pypi

Install Gemini Pro MCP in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "gemini-api-key",
      "description": "GEMINI_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "jules-api-key",
      "description": "JULES_API_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "gemini-pro-enable-flow",
      "description": "GEMINI_PRO_ENABLE_FLOW",
      "password": true
    },
    {
      "type": "promptString",
      "id": "gemini-pro-enable-browser",
      "description": "GEMINI_PRO_ENABLE_BROWSER",
      "password": true
    }
  ],
  "servers": {
    "gemini-pro-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "gemini-pro-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "${input:gemini-api-key}",
        "JULES_API_KEY": "${input:jules-api-key}",
        "GEMINI_PRO_ENABLE_FLOW": "${input:gemini-pro-enable-flow}",
        "GEMINI_PRO_ENABLE_BROWSER": "${input:gemini-pro-enable-browser}"
      }
    }
  }
}

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

Gemini Pro MCP in other clients

Gemini Pro MCP MCP server