AI Trader
Config-driven backtesting framework for algorithmic trading built on Backtrader, with an integrated MCP server that lets LLMs run and analyze backtests across stocks, crypto, and forex.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Community/specialized tool. Apply standard security practices for category. Review documentation for specific security requirements.
⚡ Reliability
Best When
You want an LLM-assisted workflow for designing, running, and analyzing backtests without writing boilerplate code.
Avoid When
You need live trading execution, real-time data feeds, or brokerage API integration. Use alpaca-mcp-server instead for actual trading.
Use Cases
- • Backtest trading strategies via YAML configs or natural language through Claude
- • Fetch historical market data for US stocks, Taiwan stocks, crypto, and forex
- • Compare and optimize 20+ built-in trading strategies
- • Develop and test custom strategies with LLM assistance
Not For
- • Live/paper trading execution (backtesting only)
- • Real-time market data streaming
- • Portfolio management or brokerage integration
Interface
Authentication
No authentication required. Uses yfinance for public market data. No API keys needed for basic usage.
Pricing
GPL-3.0 licensed. Free and open source. Market data comes from yfinance (free).
Agent Metadata
Known Gotchas
- ⚠ MCP server docs are minimal - tool list and schemas not enumerated in README
- ⚠ GPL-3.0 license requires derivative works to also be GPL - may conflict with proprietary agent deployments
- ⚠ Requires Python 3.11+ which is stricter than many MCP servers
- ⚠ yfinance data can be rate-limited or unreliable depending on Yahoo Finance availability
Alternatives
Full Evaluation Report
Detailed scoring breakdown, competitive positioning, security analysis, and improvement recommendations for AI Trader.
Scores are editorial opinions as of 2026-03-06.