Gemini MCP Server

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.

Category
访问服务器

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 tasks
  • strategic-plan - Create high-level strategic roadmaps for complex features
  • review-approach - Review and validate implementation approaches before coding

Analysis & Understanding

  • analyze-codebase - Analyze codebase structure and patterns before making changes
  • explain-concept - Get comprehensive explanations of technical concepts and patterns
  • compare-technologies - Compare different technologies, frameworks, or approaches

Development Support

  • gemini-consult - Get expert guidance when stuck on problems or need additional context
  • generate-tests - Generate comprehensive test strategies and plans
  • generate-docs - Create documentation structure and content strategies
  • debug-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

  1. Clone the repository:

    git clone https://github.com/yourusername/gemini-mcp.git
    cd gemini-mcp
    
  2. Install dependencies:

    pnpm install
    
  3. Build the project:

    pnpm build
    
  4. 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 reload
  • pnpm build - Compile TypeScript and auto-generate commands
  • pnpm generate-commands - Generate claude-commands from tool configurations
  • pnpm start - Run the compiled server
  • pnpm typecheck - Run TypeScript type checking
  • pnpm clean - Remove build artifacts

Adding New Tools

  1. Add new prompt template in src/prompts.ts
  2. Add tool configuration in src/tools.ts
  3. Implement the method in src/gemini.ts
  4. Add case in src/server.ts switch statement
  5. Run pnpm generate-commands to auto-create documentation
  6. Update this README if needed

The system automatically generates claude-commands from tool configurations, ensuring consistency.

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests if applicable
  5. Submit a pull request

License

MIT License - see LICENSE file for details

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选