Paloma DEX MCP Server

Paloma DEX MCP Server

A Model Context Protocol server that enables AI agents to autonomously execute cross-chain trading operations on Paloma DEX across seven EVM chains including Ethereum, Arbitrum, and Polygon.

Category
访问服务器

README

Paloma DEX MCP Server

A Model Context Protocol (MCP) server that enables AI agents to autonomously trade on Paloma DEX across 7 EVM chains.

Overview

This MCP server provides AI agents with tools to perform decentralized trading operations on Paloma DEX, supporting cross-chain functionality across Ethereum, Arbitrum, Optimism, Base, BSC, Polygon, and Gnosis chains. The server prioritizes automation over security by enabling autonomous transaction execution through environment-based private key management.

Features

Core Trading Tools

  • buy_token: Purchase ETF tokens or PUSD using any input token
  • sell_token: Sell ETF tokens or PUSD back to other tokens
  • get_balance: Check token balances across all 7 supported chains
  • get_price: Get current token prices

Chain Support

Supports all 7 EVM chains used by Paloma DEX:

  • Ethereum Mainnet (Chain ID: 1)
  • Arbitrum One (Chain ID: 42161)
  • Optimism (Chain ID: 10)
  • Base (Chain ID: 8453)
  • BNB Smart Chain (Chain ID: 56)
  • Polygon (Chain ID: 137)
  • Gnosis (Chain ID: 100)

Key Capabilities

  • Autonomous Trading: AI agents can execute transactions independently
  • Cross-Chain Support: Works across all Paloma DEX supported chains
  • Gas Management: Handles gas estimation and protocol fees automatically
  • Token Approvals: Automatic approval handling for ERC20 tokens
  • Error Handling: Comprehensive transaction error management
  • Contract Integration: Ready integration with PUSD and ETF connector contracts

Installation

  1. Clone the repository:

    git clone https://github.com/Cieloc/mcpPADEX.git
    cd mcpPADEX
    
  2. Install dependencies using uv:

    uv sync
    

Configuration

  1. Set up environment variables:

    cp .env.example .env
    
  2. Configure your .env file with the following required variables:

    # REQUIRED: Your private key for transaction signing
    # WARNING: Keep this secure and never commit to version control
    PRIVATE_KEY=your_private_key_here
    
    # Contract addresses for each chain (obtain from Paloma DEX)
    PUSD_TOKEN_ETH=
    PUSD_CONNECTOR_ETH=
    ETF_CONNECTOR_ETH=
    # ... (repeat for all chains)
    
    # Optional: Moralis API key for enhanced features
    MORALIS_SERVICE_API_KEY=your_moralis_api_key_here
    
  3. Obtain contract addresses from Paloma DEX documentation or team for:

    • PUSD token addresses
    • PUSD connector addresses
    • ETF connector addresses

Usage

Running the Server

uv run python main.py

The server will start and listen for MCP protocol messages via stdin/stdout.

Tool Examples

Buy Tokens

{
  "tool": "buy_token",
  "arguments": {
    "chain_id": "1",
    "input_token_address": "0xdAC17F958D2ee523a2206206994597C13D831ec7",
    "output_token_address": "0x...",
    "input_amount": "100.0",
    "slippage": 2.0
  }
}

Sell Tokens

{
  "tool": "sell_token",
  "arguments": {
    "chain_id": "1", 
    "token_address": "0x...",
    "amount": "50.0"
  }
}

Check Balances

{
  "tool": "get_balance",
  "arguments": {
    "chain_id": "1"
  }
}

Get Prices

{
  "tool": "get_price",
  "arguments": {
    "chain_id": "1",
    "token_address": "0x..."
  }
}

Architecture

Core Components

  • padex.py: Main MCP server implementation with all trading tools
  • main.py: Entry point that launches the MCP server
  • Contract ABIs: Simplified ABIs for PUSD and ETF connector interactions
  • Chain Configuration: Complete configuration for all 7 supported chains

Security Considerations

⚠️ Important Security Notes:

  • This implementation prioritizes automation over security
  • Private keys are stored in environment variables for autonomous operation
  • Ensure your .env file is never committed to version control
  • Consider using more secure key management for production use
  • The .gitignore file excludes .env by default

Dependencies

  • web3: Ethereum blockchain interaction
  • eth-account: Private key and transaction signing
  • eth-abi: ABI encoding for contract calls
  • httpx: HTTP client for API interactions
  • mcp: Model Context Protocol implementation
  • python-dotenv: Environment variable management

API Integrations

The server integrates with:

  • Paloma DEX API: For ETF data and custom pricing
  • Moralis API: For balance and price data (optional)
  • Uniswap Protocol: For swap path generation and routing

Development

Project Structure

mcpPADEX/
├── padex.py              # Main MCP server implementation
├── main.py               # Entry point
├── pyproject.toml        # Project dependencies
├── .env.example          # Environment variable template
├── .gitignore           # Git ignore rules
└── README.md            # This file

Adding New Features

The server is designed to be extensible. To add new tools:

  1. Define the tool in the handle_list_tools() method
  2. Implement the tool handler in handle_call_tool()
  3. Add the corresponding async method to the PalomaDEXServer class

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is open source. Please check the license file for details.

Disclaimer

This software is provided "as is" without warranty. Trading cryptocurrencies involves risk of loss. Use at your own risk and ensure you understand the implications of automated trading before deployment.

Support

For questions about Paloma DEX integration, consult the Paloma DEX documentation or reach out to the Paloma team.

For MCP-related questions, see the Model Context Protocol documentation.

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