
ai-trader
by whchien·★ 694·Score 52
AI trader MCP server allows LLMs to run backtests, fetch market data, and analyze trading strategies across stocks, crypto, and forex.
Overview
AI Trader is a professional backtesting framework for algorithmic trading built on Backtrader. It features a robust MCP server integration that enables AI assistants like Claude to interact with the trading engine through natural language commands. The framework supports multiple markets including US stocks, Taiwan stocks, cryptocurrencies, and forex, with over 20 built-in strategies and extensive customization options.
Try asking AI
After installing, here are 3 things you can ask your AI assistant:
When to choose this
Choose this if you're developing algorithmic trading strategies and want to integrate LLM assistants directly into your backtesting workflow through MCP.
When NOT to choose this
Don't choose this if you need a different license (it's GPL-3.0) or if you require real-time trading capabilities (it's only for backtesting).
Tools this server exposes
4 tools extracted from the READMErun_backtestRun a backtest with specified strategy and parameters
fetch_market_dataDownload historical market data for specified symbols
list_strategiesList all available trading strategies
manage_data_storageManage cached market data storage
Note: Tools were inferred from the MCP server documentation and CLI examples. The actual MCP tool names and signatures are not explicitly documented in the provided text.
Comparable tools
Installation
Installation
**Option A: Install from PyPI**
pip install ai-trader**Option B: Install from Source**
git clone https://github.com/whchien/ai-trader.git
cd ai-trader
uv syncMCP Server Configuration
**Start the Server (for testing):**
python -m ai_trader.mcp**Configure with Claude Desktop:** Add the ai-trader MCP server to your Claude Desktop configuration file:
{
"mcpServers": {
"ai-trader": {
"command": "python3",
"args": ["-m", "ai_trader.mcp"],
"cwd": "/path/to/ai-trader"
}
}
}Compare ai-trader with
Last updated · Auto-generated from public README + GitHub signals.