Gemini Image MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
git clone https://github.com/turanalemfilms-cloud/gemini-mcp-server
cd gemini-mcp-server

Then follow the repository README for any remaining dependency or build steps before continuing.

2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add -e "GEMINI_API_KEY=${GEMINI_API_KEY}" gemini-image -- node "<FULL_PATH_TO_GEMINI_MCP_SERVER>/dist/index.js"

Replace <FULL_PATH_TO_GEMINI_MCP_SERVER>/dist/index.js with the actual folder you prepared in step 1.

Required:GEMINI_API_KEY+ 3 optional
README.md

Enables image generation and prompt enhancement using Google Gemini models.

🎨 Gemini Image MCP Server

Claude.ai-ға Nano Banana (Gemini) арқылы сурет генерациясын қосатын custom MCP connector.

Жылдам старт

1. GitHub-қа жүкте

git init
git add .
git commit -m "Gemini MCP Server"
gh repo create gemini-mcp-server --public --push

2. Deploy ет (таңда біреуін)

Опция А: Railway (ұсынылады)
  1. https://railway.com → GitHub-пен кір
  2. "New Project" → "Deploy from GitHub Repo"
  3. Репозиторийді таңда
  4. Variables бөліміне қос:
    • GEMINI_API_KEY = сенің key
    • PORT = 8080
    • MCP_TRANSPORT = sse
  5. Deploy бас → URL аласың (мыс: https://gemini-mcp-server-xxx.up.railway.app)
Опция Б: Render (тегін)
  1. https://render.com → GitHub-пен кір
  2. "New Web Service" → Репозиторийді таңда
  3. Environment variables қос:
    • GEMINI_API_KEY = сенің key
    • PORT = 8080
    • MCP_TRANSPORT = sse
  4. Deploy бас → URL аласың

3. Claude.ai-ға қос

  1. https://claude.ai/settings/connectors
  2. "Add custom connector"
  3. URL: https://сенің-сервер-url/sse
  4. "Add" бас → дайын!

4. Қолдан

Claude.ai чатында жаз:

"Қазақ даласында жылқы шапқан қыз, Pixar 3D стильде сурет жаса"

Қолданылатын tool-дар

Tool Сипаттамасы
generate_image Промпт арқылы сурет генерациялау
edit_image_prompt Промптты жақсарту
list_models Қол жетімді модельдерді көрсету

Стильдер

  • photorealistic — фотореалистік
  • illustration — цифрлық иллюстрация
  • cartoon — мультфильм стилі
  • 3d_render — 3D Pixar стилі (Storyara үшін!)
  • pixel_art — пиксель арт
  • watercolor — акварель
  • oil_painting — май бояу

Environment Variables

Variable Міндетті Сипаттамасы
GEMINI_API_KEY Иә Google AI Studio API key
PORT Жоқ Сервер порты (default: 8080)
MCP_TRANSPORT Жоқ sse немесе streamable-http (default: sse)
GEMINI_IMAGE_MODEL Жоқ Gemini model ID (default: gemini-2.0-flash-exp)

Tools (3)

generate_imageGenerates an image based on a provided prompt.
edit_image_promptEnhances or modifies an existing image prompt.
list_modelsLists all available Gemini models for image generation.

Environment Variables

GEMINI_API_KEYrequiredGoogle AI Studio API key
PORTServer port (default: 8080)
MCP_TRANSPORTTransport protocol (sse or streamable-http)
GEMINI_IMAGE_MODELGemini model ID (default: gemini-2.0-flash-exp)

Configuration

claude_desktop_config.json
{ "mcpServers": { "gemini-image": { "command": "node", "args": ["path/to/server.js"], "env": { "GEMINI_API_KEY": "your_api_key_here" } } } }

Try it

→Generate an image of a girl riding a horse in the Kazakh steppe in Pixar 3D style.
→Create a photorealistic image of a futuristic city skyline at sunset.
→Improve my prompt for a watercolor painting of a mountain landscape.
→List all available Gemini models that I can use for image generation.

Frequently Asked Questions

What are the key features of Gemini Image?

Generates images using Google Gemini models. Supports multiple artistic styles including 3D render, photorealistic, and watercolor. Provides prompt enhancement tools to improve image quality. Lists available Gemini models for flexible configuration.

What can I use Gemini Image for?

Creating custom visual content for presentations or social media directly in Claude. Rapid prototyping of artistic concepts using different visual styles. Enhancing creative writing prompts with AI-generated imagery. Testing different Gemini models for image generation performance.

How do I install Gemini Image?

Install Gemini Image by running: Deploy via Railway using GitHub repository integration with GEMINI_API_KEY, PORT=8080, and MCP_TRANSPORT=sse variables.

What MCP clients work with Gemini Image?

Gemini Image works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Gemini Image docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare
View all ai-tools servers →

Related MCP Servers

Skill Seekers
The data layer for AI systems.
ai-tools11.1K stars
Context Mode
The other half of the context problem.
ai-tools5.6K stars
Semiotic
A React data visualization library designed for AI-assisted development.
ai-tools2.6K stars
RocketRide
Self-hosted, open-source AI pipeline platform for MCP tools
ai-tools1.6K stars
Context+
Semantic Intelligence for Large-Scale Engineering.
ai-tools1.5K stars
ShipSwift
AI-native SwiftUI component library — production-ready code for LLMs
ai-tools1.3K stars