Appearance
Connect via AI (MCP)
MarketHeist runs an MCP (Model Context Protocol) server so you can run real backtests, analyze portfolios and look up well-sourced portfolio statistics (seasonality, year-by-year returns, drawdowns, how diversified a portfolio really is, factor exposure, how far back a fund can be tested) directly from Claude and other MCP-compatible AI assistants — just by asking. Portfolios can hold more than funds: whole portfolios, backtested strategies and rotations can be holdings, with a trend filter on top. No account, no API key, no setup beyond adding one URL.
Connector URL
https://api.marketheist.io/api/mcp- Transport: Streamable HTTP
- Authentication: None required — all tools read public market data
- Cost: Free
Add it to Claude
- Open Settings → Connectors.
- Click Add custom connector.
- Paste the URL above and confirm.
Claude connects immediately and lists ten tools. Ask a question in plain language and Claude will call them for you.
What it can do
| Tool | What it does |
|---|---|
| Portfolio Returns and Seasonality | For a built-in model portfolio, a ready-made strategy, any ticker or your own portfolio (including nested ones): average return by calendar month (with how many years and a t-statistic, so a thin pattern is not mistaken for a law), calendar-year returns with partial years labelled and the S&P 500 beside them, trailing 1/3/5/10/20/30-year returns, and the best and worst year and month. |
| Portfolio Risk and Diversification | For a built-in portfolio, a ready-made strategy or your own portfolio (including nested ones), how bad it got and how diversified it really is: the deepest drawdowns with recovery times, Ulcer index, time underwater, monthly VaR/CVaR, returns in 2008, 2020 and 2022; each holding's share of the risk next to its share of the money; the number of independent bets over the full history, the last 10 years and the 2008 and 2022 periods; near-duplicate holdings; and the correlation matrix. For your own portfolio the independent-bets figure covers the full history (and the last 10 years for plain funds); the 2008 and 2022 periods are reported for the built-in portfolios. |
| Compare Portfolios | Two to four portfolios side by side over the same months (built-in ones and up to two of your own, nested ones included), which is the only fair comparison when their histories start at different dates: CAGR, volatility, max drawdown, Sharpe, Sortino, Ulcer index, best and worst year, time underwater, pairwise correlation and a calendar-year table. |
| Analyze Portfolio | Analyzes an asset-allocation portfolio — a built-in model (60/40, All Weather, Golden Butterfly, Permanent, Bogleheads, and more), a ready-made strategy, or a custom ticker+weight mix — and returns CAGR, max drawdown, volatility, Sharpe, and Sortino from decades of proxy-extended history. Multi-strategy and nested portfolios: a holding can also be a whole portfolio (a portfolio of portfolios), a strategy (for example the S&P 500 with a 10-month trend filter), a rotation that holds the strongest of a few funds each month, or a strategy from the public library. Optionally applies a trend-filter overlay to the whole portfolio (hold only while it's above its N-month average, else cash). Also reports the number of independent bets, the top risk driver and the same data and caveat notes as a backtest. |
| Find Guides | Searches MarketHeist's 90 published research pages (strategy guides, fund histories, trend-filter results, risk breakdowns and trading-rule robustness checks) and returns each page's verdict, headline numbers, the month they run through, its recent change log and the link to cite. |
| List Portfolios and Strategies | Lists every model portfolio, ready-made strategy and library strategy with a one-line description, holdings and headline numbers, so the other tools can be called with a valid id. |
| Fund History and Proxy Chain | How far back a fund can be tested once older substitute funds extend it, which funds stand in for it, and for the funds with a history page how closely each stand-in tracked it (close, approximate or stand-in). |
| Factor Decomposition | Explains what drives the returns of a ticker, ETF, built-in portfolio or your own portfolio by splitting them into common factor exposures (U.S. stock market, small companies, value vs. growth, momentum, quality, low volatility, interest-rate sensitivity, corporate credit) plus a leftover that is specific to the asset. Returns each exposure with its statistical strength, how much of the variance each explains, and annualized alpha; for a portfolio, also which holdings drive each factor. It is a measurement of past exposure, not a forecast. |
| Run Backtest | Runs a single-strategy backtest and returns Sharpe, CAGR, max drawdown, Calmar, Sortino, Omega, and equity/drawdown curves, benchmarked against buy-and-hold. Also reports where the data came from, known caveats (no costs, short sample, statistical significance, parameter sensitivity) and a reproducible config hash. If you give no threshold for a threshold rule, it uses the indicator's default (for example RSI above 50). For a famous setting such as the 200-day average or the golden cross on SPY, QQQ, TLT, GLD or EFA it links the robustness page that stress-tests it. |
| List Indicators | Lists the built-in indicators (RSI, Bollinger, MA/EMA Crossover, ADX, ATR, CCI, OBV, Stochastic, VWAP Deviation, and more) with their parameters and default rules. |
All ten are read-only — they analyze public market data and never modify anything.
How answers cite their sources
Every portfolio answer says which month its data runs through and links the marketheist.io pages that show the same numbers, so a statistic can be checked. Where the engine has one, the answer also carries a reproducible config hash: the same portfolio over the same months gives the same hash on the website, the API and here.
The portfolio tools that take a built-in portfolio or strategy (returns, risk, comparison, guides, listings, fund history, and Analyze Portfolio and Factor Decomposition given a model-portfolio or strategy name) answer from results prepared by the monthly data refresh. They are instant and name the last month included ("data through September 2026"); recent months appear after the next refresh. Custom allocations, nested portfolios, overlays and arbitrary tickers are computed on request from market data.
Example prompts
Try these once the connector is added. There is one for each tool:
"Is September a bad month for the 60/40 portfolio? Show me the seasonality and how reliable each month's average is." (Portfolio Returns) Returns the average return, share of positive months, number of years and a t-statistic for each calendar month of the built-in 60/40.
"Is the All Weather portfolio really diversified? How much of its risk comes from each holding, and how did it do in 2022?" (Portfolio Risk) Shows each holding's share of risk next to its share of the money, the independent-bets figures and the 2022 return and drawdowns.
"Compare 60/40, All Weather and Golden Butterfly over the same period." (Compare Portfolios) Recomputes all three on their common months and lists the metrics, correlations and calendar years side by side.
"How has the Golden Butterfly portfolio performed, and how does a 70/30 VTI/BND compare?" (Analyze Portfolio) Analyzes the built-in template and a custom allocation, with CAGR, drawdown, and Sharpe for each.
"Does the 200-day moving average work on SPY, or is it curve-fit?" (Find Guides) Finds the robustness page for that rule and reports its verdict and numbers, with the link.
"Which of the model portfolios hold gold, and how have they done?" (List Portfolios) Lists the portfolios and strategies that hold gold with their headline figures and start months.
"How far back can I test VXUS, and how well did the older fund it borrows from track it?" (Fund History) Gives the substitute fund, the extended start month and the tracking grade.
"What is driving the returns of the All Weather portfolio?" (Factor Decomposition) Splits the portfolio's returns into factor exposures and shows which holdings drive each one. A ticker works too: "What is QQQ really exposed to?"
"Backtest a weekly RSI strategy on SPY and compare it with buy-and-hold: which has the smaller drawdown?" (Run Backtest) Returns both sets of metrics side by side.
"What indicators can MarketHeist backtest, and what parameters does RSI take?" (List Indicators) Lists the indicator catalogue and the default RSI settings.
Your own portfolio on the detailed tools (Portfolio Returns, Portfolio Risk, Compare Portfolios, Factor Decomposition):
- "I hold 60% VTI, 20% VXUS and 20% BND. What did that return each calendar year, and is any month of the year reliably better?" Calendar-year returns next to the S&P 500 and the seasonality table for your mix.
- "How diversified is my portfolio of 40% Golden Butterfly, 40% All Weather and 20% QQQ, and what were its worst drawdowns?" Risk share per holding, independent bets and drawdown episodes for a portfolio of portfolios.
- "Compare my 70/30 VTI/BND with the 60/40 and All Weather over the same years." Your mix next to two built-in portfolios on their common window.
- "What is driving the returns of my 50% QQQ, 30% TLT, 20% GLD portfolio?" Factor exposures of the whole mix and the holdings behind each one.
Nested and multi-strategy portfolios (Analyze Portfolio):
- "Build 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." Holds two whole model portfolios and a fund in one portfolio and reports the result with and without the filter.
- "Make the stock side of a 60/40 a trend-following S&P 500 (in the market only above its 10-month average) and compare it with a plain 60/40." Uses a strategy as a holding next to a plain bond fund, over the same window as the plain mix.
- "Half my portfolio rotates monthly into whichever of SPY, EFA or BND had the best 12-month return; the rest is 30% VTI and 20% BND." A multi-strategy portfolio: a rotation next to fixed holdings.
Nested and multi-strategy portfolios
Most portfolio tools only let a portfolio hold funds. Here a holding can also be a whole portfolio or a strategy, so you can test a portfolio of portfolios, put a trend-following strategy inside a 60/40, or combine a rotation with fixed holdings. Your assistant builds the arguments; this is what the first nested example sends (without the filter):
json
{
"assets": [
{ "weight": 40, "sleeve": { "source": "portfolio-public", "templateId": "golden-butterfly", "label": "Golden Butterfly" } },
{ "weight": 40, "sleeve": { "source": "portfolio-public", "templateId": "all-weather", "label": "All Weather" } },
{ "ticker": "QQQ", "weight": 20 }
],
"rebalance": "yearly"
}Add "overlay": { "kind": "trend-filter", "months": 10 } to filter the whole portfolio. Other kinds of holding:
| Holding | sleeve |
|---|---|
| A built-in model portfolio | { "source": "portfolio-public", "templateId": "all-weather", "label": "All Weather" } |
| Your own mix, nested | { "source": "portfolio-mine", "portfolioId": "my-core", "label": "My core", "config": { "id": "my-core", "name": "My core", "assets": [{ "ticker": "VTI", "weight": 60 }, { "ticker": "BND", "weight": 40 }], "rebalance": "yearly" } } |
| A strategy from the public library | { "source": "backtest-public", "strategyId": "spx-golden-cross", "label": "S&P 500 Golden Cross" } |
| A rotation | { "source": "selection", "label": "Top 1 of SPY/EFA/BND", "config": { "universe": [{ "ticker": "SPY" }, { "ticker": "EFA" }, { "ticker": "BND" }], "signal": { "kind": "trailing-return", "lookbackMonths": 12, "skipMonths": 1 }, "topK": 1, "weighting": "equal", "rebalance": "monthly" } } |
| A strategy on a ticker or portfolio | { "source": "strategy-over", "label": "SPY 10-month trend", "child": { "ticker": "SPY" }, "config": { ... a full backtest configuration ... } } |
Notes:
- Everything is computed monthly, so a 10-month average stands in for the 200-day one.
- For a rotation ranked on trailing return, keep
skipMonthsat 1 so the ranking does not use the month it is about to earn. - Give every nested holding a
label; it names the holding in the result's allocation line. - Nested results report the same metrics, caveats and reproduce hash as any other portfolio. A nested portfolio counts as one holding in the independent-bets figure.
Tickers
Any symbol on Yahoo Finance works — stocks (AAPL), ETFs (SPY, QQQ), indices (^GSPC, ^NDX), crypto (BTC-USD), and commodities (GLD). History goes back as far as Yahoo has records for that symbol.
Notes
- Backtests always apply a one-bar execution delay to avoid lookahead bias.
- Results are for research and education only — they are not investment advice.
- Prefer a visual interface? Every backtest here can also be run at marketheist.io/backtest.