Gemini Image

Overview

Gemini Image is a Model Context Protocol (MCP) server: Google Gemini image generation, editing, and local processing via MCP. In practice that means any MCP-compatible AI assistant can call Gemini Image's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the npm package @jimothy-snicket/gemini-image-mcp speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need GEMINI_API_KEY. The current release is v0.5.0, published under the MIT license, with source at JimothySnicket/gemini-image-mcp on GitHub.

Gemini Image is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Gemini Image for JimothySnicket, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "gemini_image": {
      "command": "npx",
      "args": [
        "-y",
        "@jimothy-snicket/gemini-image-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "<gemini-api-key>"
      }
    }
  }
}

Requires GEMINI_API_KEY