Nexus-MCP
A comprehensive Model Context Protocol toolkit that transforms AI assistants into autonomous agents capable of executing real-world tasks across filesystems, web requests, Git workflows, databases, system commands, and AI integrations.
README
Nexus-MCP
<div align="center">
A Comprehensive Model Context Protocol Toolkit for AI Assistants
Transform any AI assistant into an autonomous agent capable of executing real-world tasks.
Documentation • Getting Started • Roadmap • Architecture
</div>
🎯 Overview
Nexus-MCP is a powerful Model Context Protocol (MCP) server built with TypeScript/Node.js that provides AI models with universal tools for:
- 📁 File System Operations - Read, write, search, and monitor files
- 🌐 HTTP/Web Requests - Fetch data, scrape websites, call APIs
- 🔄 Git Workflows - Clone, commit, branch, and manage repositories
- 🗄️ Database Queries - Query SQL and NoSQL databases
- 💻 System Commands - Execute shell commands and manage processes
- 🤖 AI Integration - Chat with LLMs, create embeddings, process text
- 🔧 Utilities - JSON/YAML parsing, compression, encryption, and more
🚀 Quick Start
Installation
npm install -g @nexus-mcp/server
Configuration
# Copy example environment file
cp .env.example .env
# Edit with your settings
nano .env
Run
nexus-mcp
Integration with Claude Code
Add to your Claude Desktop config:
{
"mcpServers": {
"nexus-mcp": {
"command": "node",
"args": ["/path/to/nexus-mcp/dist/index.js"]
}
}
}
📦 Features
Filesystem Tools
nexus_read_file- Read files with encoding supportnexus_write_file- Write/create filesnexus_list_directory- List directory contentsnexus_search_files- Search files by patternnexus_search_content- Search content within filesnexus_watch_directory- Monitor directory changes
HTTP Tools
nexus_http_get- HTTP GET requestsnexus_http_post- HTTP POST requestsnexus_fetch_url- Fetch and parse web contentnexus_parse_html- Parse HTML with Cheerionexus_call_api- Generic API calls
Git Tools
nexus_git_clone- Clone repositoriesnexus_git_commit- Create commitsnexus_git_push- Push to remotenexus_git_pr_create- Create pull requests- Integration with GitHub, GitLab, Bitbucket
Database Tools
nexus_db_query- Execute SQL queriesnexus_db_list_tables- List database tablesnexus_db_describe_table- Describe table schema- Support for PostgreSQL, MySQL, SQLite, SQL Server, MongoDB
System Tools
nexus_exec_command- Execute shell commandsnexus_system_info- Get system informationnexus_process_list- List running processesnexus_service_start/stop- Manage services
AI Tools
nexus_llm_chat- Chat with LLMs (Anthropic, OpenAI)nexus_embedding_create- Create text embeddingsnexus_text_summarize- Summarize textnexus_code_generate- Generate code
Utilities Tools
nexus_json_parse/stringify- JSON manipulationnexus_yaml_parse/stringify- YAML manipulationnexus_zip_create/extract- ZIP compressionnexus_encrypt/decrypt- Encryption/decryption
🏗️ Architecture
┌─────────────────────────────────────────┐
│ Claude / LLM Client │
└──────────────┬──────────────────────────┘
│ MCP Protocol (stdio)
▼
┌─────────────────────────────────────────┐
│ Nexus-MCP Server │
│ ┌───────────────────────────────────┐ │
│ │ MCP Server Core │ │
│ └───────────────────────────────────┘ │
│ ┌───────┴───────┐ │
│ │ │ │
│ ┌────▼────┐ ┌────▼────┐ │
│ │ Filesys │ │ HTTP │ │
│ └─────────┘ └─────────┘ │
│ ┌─────────┐ ┌─────────┐ │
│ │ Git │ │ Database│ │
│ └─────────┘ └─────────┘ │
│ ┌─────────┐ ┌─────────┐ │
│ │ System │ │ AI │ │
│ └─────────┘ └─────────┘ │
└─────────────────────────────────────────┘
For detailed architecture, see docs/architecture.md
🏛️ Production-Grade Quality
Nexus-MCP is built with architectural excellence in mind, designed for production use and community adoption. We follow strict principles:
- ✅ Type Safety: TypeScript strict mode + Zod validation
- ✅ Error Handling: Structured, actionable error messages
- ✅ Performance: Async operations, caching, streaming
- ✅ Security: Input validation, sanitization, audit logs
- ✅ Observability: Structured logging, metrics, tracing
- ✅ Testability: 80%+ coverage, dependency injection
- ✅ Documentation: JSDoc, examples, comprehensive guides
- ✅ Developer Experience: Clear errors, IDE support, quick feedback
See Architectural Principles for complete details.
📚 Documentation
- Getting Started Guide - Quick start and basic usage
- Architecture Documentation - System architecture and design
- Architectural Principles - Design principles and best practices
- API Reference - Complete API documentation
- Tools Reference - Detailed tool documentation
- Roadmap - Development roadmap and progress
🛠️ Development
# Clone repository
git clone https://github.com/your-org/Nexus-MCP.git
cd Nexus-MCP
# Install dependencies
npm install
# Run in development mode
npm run dev
# Run tests
npm test
# Build for production
npm run build
# Lint code
npm run lint
📊 Project Status
- Current Version: 1.0.0-alpha
- Development Status: Planning & Design
- Core Progress: 0%
- Target Tools: 50+
- Test Coverage Goal: 80%+
See ROADMAP.md for detailed progress.
🤝 Contributing
Contributions are welcome! Please read our contributing guidelines before submitting PRs.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
📞 Support
- 📖 Documentation
- 🐛 Issue Tracker
- 💬 Discord Community
- ✉️ Email: support@nexus-mcp.dev
<div align="center">
Built with ❤️ by the Nexus Team
</div>
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。