MarketHeist

Description

MarketHeist analyzes portfolios that hold more than funds: put whole portfolios, a trend-filtered strategy or a rotation inside one portfolio, add a filter on top, and get CAGR, drawdown and Sharpe from real price history with caveats. It also backtests indicator rules on any ticker, decomposes funds into factors, and answers cited lookups for 19 model portfolios and 7 strategies. Free, no sign-in. **What makes it different** - **Holdings can be portfolios or strategies, not only funds.** Put Golden Butterfly and All Weather inside one portfolio next to QQQ, make the stock half of a 60/40 a trend-filtered S&P 500, or hold a rotation that picks the strongest of SPY, EFA and BND each month. - **Filters on top.** A trend filter can wrap the whole book (hold it only while it is above its own 10-month average, else cash) or one holding. - **Same numbers as a plain portfolio.** Nested results come with the same CAGR, drawdown, Sharpe, risk split, caveats and reproduce hash. - **Cited lookups (new in 1.2.0).** Seasonality with t-statistics, calendar-year returns, drawdown episodes, share of risk vs share of money, independent bets, side-by-side comparisons over a common window and fund history. Precomputed, so answers are instant, say which month the data runs through and link the marketheist.io page with the same number. **New in 1.3.0:** the returns, risk, comparison and factor tools also take your own portfolio, nested ones included, computed live, and portfolio_returns takes any ticker. **Try asking** - "Build me a portfolio of portfolios: 40% Golden Butterfly, 40% All Weather and 20% QQQ, rebalanced yearly. Then add a 10-month trend filter on the whole thing." - "Is 60/40 really diversified, and how did All Weather do in 2022?" - "Compare 60/40, All Weather and Golden Butterfly over the same period." - "Backtest a 50/200-day golden cross on SPY with daily data and 5 bps costs, against buy-and-hold." **Tools (10, all read-only):** portfolio_returns, portfolio_risk, compare_portfolios, analyze_portfolio, find_guides, list_portfolios, fund_history, decompose_factors, run_backtest, list_indicators. Every number is computed by a deterministic engine on real price data, and the server reports its caveats with each result. Historical simulation for research and education, not investment advice. Docs: https://marketheist.io/docs/reference/mcp

Community Metrics

Categories

• mcp

Tags

• mcp
• smithery

Capabilities

• remote

Information