Cryptocurrency Market Data MCP Server
A Model Context Protocol (MCP) server that provides real-time and historical cryptocurrency market data through integration with major exchanges. This server enables LLMs like Claude to fetch current prices, analyze market trends, and access detailed trading information.
Features
Real-time Market Data
- Current cryptocurrency prices
- Market summaries with bid/ask spreads
- Top trading pairs by volume
- Multiple exchange support
Historical Analysis
- OHLCV (candlestick) data
- Price change statistics
- Volume history tracking
- Customizable timeframes
Exchange Support
- Binance
- Coinbase
- Kraken
- KuCoin
- HyperLiquid
- Huobi
- Bitfinex
- Bybit
- OKX
- MEXC
Installation
# Using uv (recommended)
uv pip install mcp ccxt
# Using pip
pip install mcp ccxt
Usage
Running the Server
python crypto_server.py
Connecting with Claude Desktop
- Open your Claude Desktop configuration at:
* macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
* Windows: `%APPDATA%\Claude\claude_desktop_config.json`
- Add the server configuration:
{
"mcpServers": {
"crypto": {
"command": "python",
"args": ["/path/to/crypto_server.py"]
}
}
}
- Restart Claude Desktop
Available Tools
- get-price
* Get current price for any trading pair
* Example: "What's the current price of BTC/USDT on Binance?"
- get-market-summary
* Fetch detailed market information
* Example: "Show me a market summary for ETH/USDT"
- get-top-volumes
* List top trading pairs by volume
* Example: "What are the top 5 trading pairs on Kraken?"
- list-exchanges
* Show all supported exchanges
* Example: "Which exchanges are supported?"
- get-historical-ohlcv
* Get historical candlestick data
* Example: "Show me the last 7 days of BTC/USDT price data in 1-hour intervals"
- get-price-change
* Calculate price changes over different timeframes
* Example: "What's the 24-hour price change for SOL/USDT?"
- get-volume-history
* Track trading volume over time
* Example: "Show me the trading volume history for ETH/USDT over the last week"
Example Queries
Here are some example questions you can ask Claude once the server is connected:
- What's the current Bitcoin price on Binance?
- Show me the top 5 trading pairs by volume on Coinbase
- How has ETH/USDT performed over the last 24 hours?
- Give me a detailed market summary for SOL/USDT on Kraken
- What's the trading volume history for BNB/USDT over the last week?
Technical Details
Dependencies
mcp: Model Context Protocol SDKccxt: Cryptocurrency Exchange Trading Library- Python 3.9 or higher
Architecture
The server uses:
- CCXT's async support for efficient exchange communication
- MCP's tool system for LLM integration
- Standardized data formatting for consistent outputs
- Connection pooling for optimal performance
Error Handling
The server implements robust error handling for:
- Invalid trading pairs
- Exchange connectivity issues
- Rate limiting
- Malformed requests
- Network timeouts
Development
Running Tests
# To be implemented
pytest tests/
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
Local Development
# Clone the repository
git clone [repository-url]
cd crypto-mcp-server
# Install dependencies
uv pip install -e .
Troubleshooting
Common Issues
- Exchange Connection Errors
* Check your internet connection
* Verify the exchange is operational
* Ensure the trading pair exists on the selected exchange
- Rate Limiting
* Implement delays between requests
* Use different exchanges for high-frequency queries
* Check exchange-specific rate limits
- Data Formatting Issues
* Verify trading pair format (e.g., BTC/USDT, not BTCUSDT)
* Check timeframe specifications
* Ensure numerical parameters are within valid ranges
License
MIT License - See LICENSE file for details
Acknowledgments
- CCXT for exchange integrations
- Model Context Protocol for the MCP specification
- The cryptocurrency exchanges for providing market data APIs
