drio
Open app

Gemini MCP Server for Claude Desktop

Source

A Model Context Protocol (MCP) server that enables Claude Desktop to generate images using Google's Gemini AI

Catalog onlyCatalog onlySTDIO

Overview

Gemini MCP Server is a Model Context Protocol (MCP) server that allows Claude Desktop to generate images using Google's Gemini AI models.

To use the Gemini MCP Server, install it via npm, run the setup wizard to configure it with your Google Gemini API key, and then interact with Claude Desktop to generate images by providing prompts.

  • Generate images directly from Claude Desktop using Google's Gemini models - Easy setup wizard for configuration - Customizable image generation parameters - Integration with Claude Desktop's MCP server system - Detailed logging and debugging capabilities
  1. Generating artistic images based on user prompts.
  2. Creating illustrations for creative projects.
  3. Assisting in visual content creation for presentations.

Add to your AI client

Use these steps to connect Gemini MCP Server for Claude Desktop in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "gemini-mcp-server-garblesnarff": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gemini-mcp-server-garblesnarff"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "gemini-mcp-server-garblesnarff": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gemini-mcp-server-garblesnarff"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "gemini-mcp-server-garblesnarff": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gemini-mcp-server-garblesnarff"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "gemini-mcp-server-garblesnarff": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gemini-mcp-server-garblesnarff"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "gemini-mcp-server-garblesnarff": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gemini-mcp-server-garblesnarff"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "gemini-mcp-server-garblesnarff": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-gemini-mcp-server-garblesnarff"
      ]
    }
  }
}

FAQ

Can I use my own images with Gemini MCP Server?

No, the server generates images based on prompts provided to Claude.

Is there a cost associated with using the Google Gemini API?

Yes, usage of the Google Gemini API may incur costs based on the API's pricing structure.

What if the server doesn't start?

Check the log file for errors, verify your API key, and ensure all directories exist and have proper permissions.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":3183,"uuid":"96eb621d-6152-4b1a-8597-90d70d72442f","name":"gemini-mcp-server","title":"Gemini MCP Server for Claude Desktop","description":"A Model Context Protocol (MCP) server that enables Claude Desktop to generate images using Google's Gemini AI","avatar_url":"https://avatars.githubusercontent.com/u/164594984?v=4","created_at":"2025-03-18T03:14:06.683Z","updated_at":"2025-03-18T14:24:32.265Z","status":"created","author_name":"Garblesnarff","author_avatar_url":"https://avatars.githubusercontent.com/u/164594984?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/Garblesnarff/gemini-mcp-server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"1\",\"license\":\"MIT license\",\"language\":\"JavaScript\",\"is_official\":false,\"latest_commit_time\":\"2025-04-26 22:10:48\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]