Binance MCP Server
Enables automated cryptocurrency trading on Binance and provides integration for monitoring Base network operations. It allows users to execute trades, fetch market data, and calculate technical indicators like RSI and MACD through the Model Context Protocol.
README
Binance MCP Server
A Model Context Protocol (MCP) server for cryptocurrency trading on Binance and Base network interactions. This server provides tools for automated trading, market analysis, and blockchain operations.
Features
- Binance Trading Tools: Place orders, check balances, fetch market data, and calculate technical indicators.
- Base Network Integration: Monitor blockchain status and prepare for DeFi operations.
- Technical Analysis: Built-in RSI, MACD, Bollinger Bands, and moving averages.
- Secure API Handling: Environment variables for API keys.
Installation
-
Clone or navigate to the project directory.
-
Create a virtual environment:
python3 -m venv .venv -
Activate the virtual environment:
source .venv/bin/activate # On Windows: .venv\Scripts\activate -
Upgrade pip and install dependencies:
pip install --upgrade pip pip install -r requirements.txt
Environment Variables
Create a .env file in the root directory with your API credentials:
# Binance API Configuration
BINANCE_API_KEY=your_binance_api_key_here
BINANCE_SECRET_KEY=your_binance_secret_key_here
Security Note: Never commit the .env file to version control. It is already included in .gitignore.
Running the MCP Server
Start the server with Server-Sent Events (SSE) transport:
python mcp_server.py
The server will run on http://127.0.0.1:8080/sse by default.
Available Tools
The MCP server exposes the following tools for integration with AI agents:
Trading Tools
get_account_balance(asset="USDT"): Get balance for a specific asset.get_market_price(symbol="BTCUSDT"): Get current market price.fetch_chart_data(symbol="BTCUSDT", interval="1h", limit=100): Fetch historical OHLCV data.calculate_indicators(symbol="BTCUSDT", interval="1h", limit=100): Calculate technical indicators (RSI, MACD, Bollinger Bands, etc.).get_symbol_rules(symbol="BTCUSDT"): Get trading rules and precision requirements.adjust_leverage(symbol="BTCUSDT", leverage=5): Adjust leverage for futures trading.place_order(symbol="BTCUSDT", side="BUY", quantity=0.001): Place a market order.
Blockchain Tools
get_base_network_status(): Check Base network health (block number, gas price).
Utility Tools
read_bot_logs(lines=20, log_type="general"): Read bot logs for debugging.
Testing
Run the tests to verify functionality:
python -m pytest tests/
Or run a specific test:
python tests/test_mcp_registration.py
Configuration
Trading parameters can be adjusted in config.py:
TRADING_PAIRS: List of symbols to trade.MIN_ORDER_VALUE: Minimum order value in USDT.STOP_LOSS_PERCENTAGE: Stop loss percentage.TAKE_PROFIT_PERCENTAGE: Take profit percentage.POLLING_INTERVAL: Time between checks (in seconds).
Security Considerations
- Use testnet for initial testing.
- Implement proper risk management.
- Monitor API rate limits.
- Keep API keys secure and rotate regularly.
Contributing
- Fork the repository.
- Create a feature branch.
- Make your changes.
- Add tests for new functionality.
- Submit a pull request.
License
This project is licensed under the MIT License.
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。