Backtest for Claude, Cursor, ChatGPT & agents

Portfolio backtesting on public daily data, key-free: replay an asset allocation — or the user's live TradeLoop portfolio

curl -fsSL https://tradeloop.top/install.sh | sh

What it does

Portfolio backtesting on public daily data, key-free: replay an asset allocation — or the user's live TradeLoop portfolio — over history with rebalancing (none/monthly/quarterly/yearly/threshold) and optional DCA, against a mandatory benchmark (default SPY). Returns CAGR, volatility, Sharpe/Sortino, max drawdown with dates and length, yearly returns, per-asset contribution, money-weighted (XIRR) vs time-weighted returns when DCA flows are involved, and an equity+drawdown chart PNG the agent/user can see. Honesty built in: start date clamping, dividends-reinvested assumption, survivorship bias and rf=0 are all disclosed in every result; history is never presented as a forecast.

The Backtest skill is one of 40+ pre-wired TradeLoop integrations that any MCP-compatible client — Claude Desktop, Claude Code, Cursor, Windsurf, Codex CLI, and ChatGPT desktop — can call out of the box. You don't configure MCP servers or copy API keys into a JSON file; the TradeLoop daemon discovers the skill at startup and exposes its tools to whichever AI client is running.

Sample prompts

Once TradeLoop is installed and Backtest is connected, ask your agent something like:

• “Portfolio Replay replay from Backtest.”
• “Use the Backtest skill from TradeLoop to portfolio replay.”
• “Use the Backtest skill from TradeLoop to portfolio replay.”

Tools available (1)

• backtest__portfolio_replay

  Replay an asset allocation over history ('60/40 组合过去十年表现如何', '回测我的组合'). holdings: [{symbol, weight}] (weights normalized; omit all weights for equal-weight; omit holdings entirely to replay the user's live portfolio positions weighted by current value). period: 1y/2y/3y/5y/10y/ytd/max (default 5y; start clamps to the y

How to connect

Backtest is a no-auth skill — there's nothing to connect. Once TradeLoop is installed, your agent can call its tools immediately.

1. Run curl -fsSL https://tradeloop.top/install.sh | sh on macOS / Linux (or the PowerShell command on Windows).
2. Run tradeloop login to create your account and a device-bound encryption key.
3. Run tradeloop update to sync the skill + credentials to every installed AI client.

Pricing

Free at every TradeLoop tier. Connect your account once at /connect; the OAuth or API-key credential stays encrypted on your machine and syncs to your other devices via the TradeLoop vault.

See the full TradeLoop pricing breakdown — Free $0/mo, Pro $29/mo, Ultra $99/mo — on the homepage.