Gemini MCP Server
Integrates Google's Gemini AI with Claude Code to provide advanced development assistance including code analysis, implementation planning, technical explanations, debugging support, and strategic development guidance.
README
Gemini MCP Server
A Model Context Protocol (MCP) server that integrates Google's Gemini AI with Claude Code for enhanced development workflows.
<video src="https://github.com/user-attachments/assets/5aa59a83-0ce5-4a58-976f-1d717517bee9" controls> </video>
Overview
This MCP server provides Claude Code with access to Gemini AI capabilities for advanced code analysis, planning, and consultation. It bridges the gap between Claude's development assistance and Gemini's powerful language understanding, offering a comprehensive AI-powered development experience.
Features
Current Tools
Planning & Strategy
generate-plan- Generate detailed implementation plans for development tasksstrategic-plan- Create high-level strategic roadmaps for complex featuresreview-approach- Review and validate implementation approaches before coding
Analysis & Understanding
analyze-codebase- Analyze codebase structure and patterns before making changesexplain-concept- Get comprehensive explanations of technical concepts and patternscompare-technologies- Compare different technologies, frameworks, or approaches
Development Support
gemini-consult- Get expert guidance when stuck on problems or need additional contextgenerate-tests- Generate comprehensive test strategies and plansgenerate-docs- Create documentation structure and content strategiesdebug-assist- Analyze errors and get systematic debugging assistance
Claude Commands
Each tool is accessible via Claude Code commands:
Planning & Strategy
/plan- Generate detailed implementation plans/strategy- Create strategic roadmaps for complex features/review- Review and validate implementation approaches
Analysis & Understanding
/analyze- Analyze codebase architecture and patterns/explain- Get comprehensive explanations of technical concepts/compare- Compare technologies, frameworks, or approaches
Development Support
/consult- Get expert guidance and development advice/tests- Generate comprehensive test strategies/docs- Create documentation structure and strategies/debug- Get systematic debugging assistance
Prerequisites
- Node.js 18+ and pnpm
- Gemini CLI installed and configured
- Valid Google AI API credentials for Gemini access
- Claude Code CLI
Installation
-
Clone the repository:
git clone https://github.com/yourusername/gemini-mcp.git cd gemini-mcp -
Install dependencies:
pnpm install -
Build the project:
pnpm build -
Configure Gemini CLI with your API credentials:
gemini auth login
Usage
Running the Server
For development:
pnpm dev
For production:
pnpm start
Integration with Claude Code
Add this server to your Claude Code configuration:
claude mcp add gemini-mcp node /path/to/dist/index.js
Adding custom commands
Copy the content of claude-commands to your .claude/commands folder
cp claude-commands/* ./claude/commands
Using the Tools
Once configured, you can use the tools directly in Claude Code:
Planning and Strategy
/plan Add user authentication with JWT tokens
/strategy Real-time chat system | WebSocket connections, message persistence, user presence
/review I plan to use Redux Toolkit with RTK Query for state management
Analysis and Understanding
/analyze [select files/folders to analyze their architecture]
/explain event loop in Node.js and asynchronous operations
/compare React vs Vue for building a dashboard application
Development Support
/consult How should I structure error handling in my React app?
/tests UserAuthenticationService with login, logout, and password reset methods
/docs REST API endpoints for user management system
/debug TypeError: Cannot read property 'map' of undefined in React component
Development
Project Structure
├── src/
│ ├── index.ts # Entry point
│ ├── server.ts # MCP server setup and tool registration
│ ├── gemini.ts # Gemini client wrapper
│ ├── prompts.ts # Structured prompt templates
│ ├── tools.ts # Tool configurations and metadata
│ └── generateCommands.ts # Auto-generates claude-commands
├── claude-commands/ # Auto-generated Claude command docs
│ ├── plan.md, strategy.md, review.md
│ ├── analyze.md, explain.md, compare.md
│ ├── consult.md, tests.md, docs.md
│ └── debug.md
├── dist/ # Compiled output
└── package.json
Available Scripts
pnpm dev- Run in development mode with hot reloadpnpm build- Compile TypeScript and auto-generate commandspnpm generate-commands- Generate claude-commands from tool configurationspnpm start- Run the compiled serverpnpm typecheck- Run TypeScript type checkingpnpm clean- Remove build artifacts
Adding New Tools
- Add new prompt template in
src/prompts.ts - Add tool configuration in
src/tools.ts - Implement the method in
src/gemini.ts - Add case in
src/server.tsswitch statement - Run
pnpm generate-commandsto auto-create documentation - Update this README if needed
The system automatically generates claude-commands from tool configurations, ensuring consistency.
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT License - see LICENSE file for details
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。