Claude-to-Gemini MCP Server

An Agent-to-Agent integration project using Google Gemini as an MCP (Model Context Protocol) server in Claude Code.

🎯 Project Purpose

• Claude Code: Main AI (general coding, debugging, file creation/modification)

• Gemini: Sub AI (large-scale context analysis, codebase review, 6 types of specialized image generation)

Related MCP server: Claude Code Gemini MCP

✨ Key Features

1. ask_gemini - Text/Code Generation

• Purpose: General Gemini calls, large context analysis

• Model Selection:

  • flash (default): Gemini 2.5 Flash - Free, fast

  • pro: Gemini 3.1 Pro - Latest model (released Feb 2026), highest performance

• Context: Up to 1M tokens

2. gemini_analyze_codebase - Codebase Analysis

• Purpose: Comprehensive analysis of the entire codebase

• Analysis Types:

  • architecture: Architecture pattern analysis

  • duplications: Duplicate code detection

  • security: Security vulnerability scan

  • performance: Performance optimization opportunities

  • general: Comprehensive analysis

3. generate_logo - Logo/Icon Generation

• Purpose: Creating logos, icons, and branding assets

• Model: Nano Banana Pro (gemini-3-pro-image-preview) - Specialized for professional asset creation

• Parameters:

  • prompt: Logo description (English)

  • brandName: Brand/text name to include (optional)

  • style: minimal | modern | vintage | playful | corporate

  • colorScheme: Color palette (optional)

• Features: Simple and scalable design, 1:1 ratio default

4. generate_illustration - Illustration/Artwork Generation

• Purpose: Illustrations, artwork, characters, concept art

• Model: Nano Banana 2 (gemini-3.1-flash-image-preview) - Fast generation, free

• Parameters:

  • prompt: Illustration description (English)

  • style: watercolor | cartoon | vector | oil_painting | sketch | anime | pixel_art

  • mood: cheerful | dark | calm | dramatic (optional)

  • aspectRatio: 1:1 | 16:9 | 9:16 | 4:3 | 3:4

  • numberOfImages: Number of images to generate (1-4)

5. generate_infographic - Infographic/Diagram Generation

• Purpose: Infographics, diagrams, flowcharts, timelines

• Model: Nano Banana Pro (gemini-3-pro-image-preview) - Thinking mode + text rendering optimization

• Parameters:

  • prompt: Infographic topic/content (English)

  • data: Data/information to visualize (optional)

  • type: infographic | diagram | flowchart | timeline | comparison | stats

  • aspectRatio: 1:2 (default) | 1:4 | 1:1 | 16:9

• Features: Easy-to-read text rendering, supports vertical long layouts

6. generate_photo - Realistic Photo Generation

• Purpose: Photorealistic images, product mockups, advertising photos

• Model: Imagen 4 (imagen-4.0-generate-001) - Highest realistic quality, paid

• Parameters:

  • prompt: Photo description (English)

  • style: natural | studio | cinematic | aerial | macro

  • numberOfImages: Number of images to generate (1-4)

  • aspectRatio: 1:1 | 16:9 | 9:16 | 4:3 | 3:4

• Features: Up to 4K resolution, includes automatic SynthID watermark

7. generate_banner - Marketing Banner/SNS Image Generation

• Purpose: Marketing banners, SNS images, thumbnails, posters

• Model: Nano Banana Pro (gemini-3-pro-image-preview) - Text + graphic combination

• Parameters:

  • prompt: Banner description (English)

  • text: Text to include in the banner (optional)

  • platform: facebook | instagram | twitter | youtube | linkedin | web

  • aspectRatio: Automatic setting per platform

• Features: Provides optimized size presets for each platform

8. edit_image - Image Editing/Modification

• Purpose: Adding/deleting/modifying elements in existing images

• Model: Nano Banana 2 (gemini-3.1-flash-image-preview) - Free

• Parameters:

  • prompt: Editing instructions (English)

  • imagePath: Path to the image file to edit

  • action: modify | add | remove | style_transfer | enhance

• Features: Interleaved editing, supports multi-turn conversational modifications

🛠 Tech Stack

• Runtime: Node.js 18+

• MCP SDK: @modelcontextprotocol/sdk

• AI API: Google Gemini API (@google/generative-ai)

• IDE: Claude Code (CLI + VSCode extension)

📦 Installation

1. Prerequisites

• Node.js 18 or higher

• Claude Pro/Max plan subscription

• Google Gemini API key (ai.google.dev)

2. Clone the Project

git clone https://github.com/YOUR_USERNAME/claude-to-gemini.git
cd claude-to-gemini

3. Install Dependencies

npm install

4. Register MCP Server

claude mcp add gemini \
  --env GEMINI_API_KEY=YOUR_API_KEY_HERE \
  -- node /ABSOLUTE_PATH/claude-to-gemini/index.js

Note:

• Replace YOUR_API_KEY_HERE with your actual Gemini API key

• Replace /ABSOLUTE_PATH/ with the actual project path (e.g., /Users/username/projects/claude-to-gemini/index.js)

5. Verification

claude mcp list

Output example:

gemini - node /Users/username/projects/claude-to-gemini/index.js

🚀 Usage

Start Claude Code

claude

Basic Usage (Flash model, free)

ask_gemini 도구를 사용해서 "이 프로젝트 전체 구조를 분석해줘" 물어봐줘

Pro Model Usage (Paid, high performance)

ask_gemini 도구를 사용해서 model을 "pro"로 설정하고 "복잡한 아키텍처 설계해줘" 물어봐줘

Codebase Analysis

gemini_analyze_codebase 도구로 보안 취약점을 찾아줘

Logo Generation

generate_logo 도구로 brandName을 "CafeKiosk"로, style을 "modern"으로 설정하고
"A minimalist coffee cup logo with geometric shapes" 로고 만들어줘

Illustration Generation (Free)

generate_illustration 도구로 style을 "watercolor"로 설정하고
"A cozy cafe interior with warm lighting" 삽화 생성해줘

Infographic Generation

generate_infographic 도구로 type을 "flowchart"로 설정하고
"User authentication flow: login, verify, 2FA, dashboard" 다이어그램 만들어줘

Realistic Photo Generation (Paid - Imagen 4)

generate_photo 도구로 style을 "studio"로, numberOfImages를 4로 설정하고
"Professional food photography of a latte with beautiful latte art" 이미지 4개 생성해줘

Marketing Banner Generation

generate_banner 도구로 platform을 "instagram"으로 설정하고
text를 "Grand Opening 50% OFF"로
"Bright modern cafe promotion banner with coffee beans" 배너 만들어줘

Image Editing (Free)

edit_image 도구로 action을 "remove"로, imagePath를 "./photo.png"으로 설정하고
"Remove the background person and keep only the coffee cup" 편집해줘

💡 Use Cases

Scenario 1: Designing New Project Architecture

ask_gemini 도구로 React + Express + PostgreSQL
전자상거래 앱의 전체 아키텍처를 설계해줘

Scenario 2: Legacy Code Analysis

gemini_analyze_codebase 도구로
focus를 'duplications'로 설정해서 중복 코드를 찾아줘

Scenario 3: Large-scale Refactoring

ask_gemini 도구로 이 프로젝트 전체를 읽고
모던한 아키텍처로 마이그레이션 계획을 세워줘

📚 Practical Guide

How to use it in practice?

For more detailed practical usage, refer to the 📖 Practical Usage Guide (USECASES.md)!

Key Contents:

• 🔍 Junior Code Review (Daily morning routine)

• 🏗️ Large-scale Refactoring (1200-line migration)

• 🚀 Project Onboarding (Grasp core concepts within 1 hour)

• 🎨 Architecture Design (Monorepo structure)

• 🖼️ Specialized Image Generation (Logo, illustration, infographic, photo, banner, editing)

• 💡 Tips and Tricks (Cost optimization, model selection)

📊 Model Comparison

Text/Code Generation Models

Image Generation Models

⚠️ Security Precautions

API Key Protection

Strictly Prohibited:

• ❌ Uploading API keys to GitHub

• ❌ Hardcoding API keys in code

• ❌ Sharing API keys in public places

Recommendations:

• ✅ Manage only via environment variables

• ✅ Include .claude.json in .gitignore

• ✅ Reissue immediately if API key is leaked

Required .gitignore Content

node_modules/
.claude.json
.env
*.key

🤝 How to Contribute

1. Fork the Project

2. Create your Feature Branch (git checkout -b feature/AmazingFeature)

3. Commit your Changes (git commit -m 'Add some AmazingFeature')

4. Push to the Branch (git push origin feature/AmazingFeature)

5. Open a Pull Request

📝 License

MIT License - See the LICENSE file for details

🔗 References

• MCP Official Documentation

• Gemini API Documentation

• Claude Code Documentation

📧 Contact

Project-related inquiries: GitHub Issues

Made with ❤️ by [Your Name]