AURA MCP Server
Enables Claude and ChatGPT to interact with AdEx AURA API for DeFi portfolio analysis, yield opportunity scanning, and automated trading strategy execution across multiple EVM chains. Includes risk management guardrails and on-chain payment verification.
README
🚀 AURA MCP Server
Bridge LLMs with AURA API and EVM for on-chain intelligence
A modular Model Context Protocol (MCP) server that enables Claude & ChatGPT to interact with AdEx AURA for DeFi portfolio analysis, yield opportunities, and automated trading strategies.
🌟 Features
🔗 MCP Commands
portfolio.getBalance- Get wallet balance across chainsportfolio.getPositions- Get DeFi positions and health factorsoperations.scanOpportunities- Scan for yield and airdrop opportunitiesstrategy.propose- Propose DCA or liquidation guard strategiesstrategy.backtest- Backtest strategy performancetransaction.simulate- Simulate transaction executiontransaction.execute- Execute transactions with guard validationguard.setRules- Configure risk management rulesreport.get- Get trading history and PnLsystem.health- Check system status
🛡️ Guard Engine
- Risk Management: Max slippage, gas limits, health factors
- Route Protection: Allowed DEXes, blocked tokens/protocols
- Emergency Stop: Instant transaction blocking
- Dynamic Rules: Per-user customizable guardrails
💰 x402 Paywall
- On-chain payment verification
- Per-request monetization
- USDC/USDT payment support
- Invoice generation and tracking
🔌 Strategy Plugins
- DCA Event-Aware: Dollar-cost averaging with market event detection
- Liquidation Guard: Automated position protection
🚀 Quick Start
Installation
git clone https://github.com/aura-mcp/server.git
cd aura-mcp-server
npm install
Configuration
cp .env.example .env
# Edit .env with your configuration
Development
# Start development server
npm run dev
# Run tests
npm test
# Build for production
npm run build
Production
# Build and start
npm run build
npm start
⚙️ Configuration
Environment Variables
# AURA Configuration
AURA_API_URL=https://api.aura.adex.network
AURA_API_KEY=your_aura_api_key
# RPC Endpoints
RPC_ETHEREUM=https://eth-mainnet.g.alchemy.com/v2/YOUR_KEY
RPC_BASE=https://mainnet.base.org
RPC_ARBITRUM=https://arb1.arbitrum.io/rpc
# x402 Payment
X402_RECEIVER=0xYourWalletAddress
X402_ASSET=USDC
# Server
MCP_SERVER_PORT=3000
NODE_ENV=production
📖 Usage Examples
Portfolio Analysis
// Get wallet balance
const balance = await mcpClient.call('portfolio.getBalance', {
address: '0x69bfD720Dd188B8BB04C4b4D24442D3c15576D10',
chain: 'ethereum'
});
// Get DeFi positions
const positions = await mcpClient.call('portfolio.getPositions', {
address: '0x69bfD720Dd188B8BB04C4b4D24442D3c15576D10'
});
Strategy Proposal
// DCA Event-Aware Strategy
const strategy = await mcpClient.call('strategy.propose', {
intent: 'dca_event_aware',
params: {
asset: 'ETH',
budgetUsd: 200,
cadence: '2x/week',
eventRules: {
pauseOnUnlock: true,
maxGasGwei: 25,
boostOnDrawdownPct: 3
}
},
address: '0x69bfD720Dd188B8BB04C4b4D24442D3c15576D10'
});
Transaction Execution
// Simulate transaction
const simulation = await mcpClient.call('transaction.simulate', {
intentId: 'dca_event_aware_123',
txParams: {
to: '0x1234...',
value: '100000000000000000',
gasLimit: '150000'
}
});
// Execute if simulation passes
if (simulation.ok) {
const execution = await mcpClient.call('transaction.execute', {
intentId: 'dca_event_aware_123',
txParams: simulation.txParams
});
}
🏗️ Architecture
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Claude/ChatGPT│ │ AURA MCP Server│ │ AURA API/SDK │
│ │◄──►│ │◄──►│ │
│ - Tool Calls │ │ - MCP Protocol │ │ - Portfolio │
│ - Responses │ │ - Guard Engine │ │ - Strategies │
│ - Context │ │ - x402 Paywall │ │ - Analytics │
└─────────────────┘ └─────────────────┘ └─────────────────┘
│
▼
┌─────────────────┐
│ EVM Chains │
│ │
│ - Ethereum │
│ - Base │
│ - Arbitrum │
│ - Polygon │
└─────────────────┘
🧪 Testing
# Run all tests
npm test
# Run with coverage
npm test -- --coverage
# Run specific test
npm test -- --testNamePattern="Guard Engine"
🚀 Deployment
Vercel
npm i -g vercel
vercel --prod
Railway
npm i -g @railway/cli
railway login
railway up
Docker
docker build -t aura-mcp-server .
docker run -p 3000:3000 aura-mcp-server
📊 Performance
- Response Time: < 2s for portfolio analysis
- Throughput: 100+ requests/minute
- Uptime: 99.9% SLA
- Security: Guard engine protection
🔒 Security
- Input validation with Zod schemas
- Guard engine risk management
- x402 payment verification
- Rate limiting and DDoS protection
- Encrypted environment variables
🤝 Contributing
- Fork the repository
- Create feature branch (
git checkout -b feature/amazing-feature) - Commit changes (
git commit -m 'Add amazing feature') - Push to branch (
git push origin feature/amazing-feature) - Open Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🏆 Hackathon Submission
Project: AURA MCP Server
Event: AdEx AURA Hackathon
Deadline: October 22, 2025
Status: ✅ Ready for submission
Demo Links
- Live Demo: https://aura-mcp-hackathon.vercel.app
- Video Demo: https://youtube.com/watch?v=your-demo-video
- GitHub: https://github.com/aura-mcp/server
Key Features Demonstrated
- ✅ Portfolio analysis across multiple chains
- ✅ DCA Event-Aware strategy automation
- ✅ Liquidation guard protection
- ✅ x402 paywall monetization
- ✅ Guard engine risk management
- ✅ Real-time transaction simulation
📞 Support
- Documentation: docs.aura-mcp.dev
- Issues: GitHub Issues
- Discord: AURA Community
- Email: support@aura-mcp.dev
Built with ❤️ for the AURA community
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。