Real Return Engine is an MCP server published by com.realreturnengine, hosted at realreturnengine.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 4 tools, including get_cross_asset_7y_forecast, get_100yr_backtest_summary, explain_methodology, request_missing_asset_or_feature.
7-year expected real and nominal returns for Cash, Bonds, and S&P 500 (1928-2026 backtest).
706 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Returns 7-year expected annualized real (after-inflation) and nominal returns (%/yr), current real yields, ETF proxy tickers (BIL, SHV, SGOV, IEF, GOVT, TLT, LQD, VCIT, SPY, VOO, IVV), and return-basis assumptions across US Cash (3-Month Treasury Bill), 10-Year US Government Bonds, Investment-Grade Corporate Bonds (Moody's Baa), and the S&P 500 under four valuation frameworks: Post-1990 Baseline, 100-Year Baseline, Robert Shiller 10-Year Government Bond CAPE (Excess CAPE Yield / ECY), and Standard Raw Shiller CAPE (cyclically adjusted P/E ratio).
No parameters.
{
"name": "get_cross_asset_7y_forecast",
"title": "Get 7-Year Cross-Asset Expected Returns",
"description": "Returns 7-year expected annualized real (after-inflation) and nominal returns (%/yr), current real yields, ETF proxy tickers (BIL, SHV, SGOV, IEF, GOVT, TLT, LQD, VCIT, SPY, VOO, IVV), and return-basis assumptions across US Cash (3-Month Treasury Bill), 10-Year US Government Bonds, Investment-Grade Corporate Bonds (Moody's Baa), and the S&P 500 under four valuation frameworks: Post-1990 Baseline, 100-Year Baseline, Robert Shiller 10-Year Government Bond CAPE (Excess CAPE Yield / ECY), and Standard Raw Shiller CAPE (cyclically adjusted P/E ratio).",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "Get 7-Year Cross-Asset Expected Returns",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Returns 100-year historical out-of-sample forecast accuracy metrics (1928-2026 evaluation window, 100-Year Mean Absolute Error, Post-1990 Mean Absolute Error, and Pearson correlation r across 92 completed 7-year periods) plus historical market turning-point snapshots comparing expected vs. realized 7-year real returns at the 1982 Interest Rate Peak, 2000 Dot-Com Bubble Peak, 2009 Financial Crisis Low, and Live 2026.
No parameters.
{
"name": "get_100yr_backtest_summary",
"title": "Get 100-Year Historical Backtest Summary",
"description": "Returns 100-year historical out-of-sample forecast accuracy metrics (1928-2026 evaluation window, 100-Year Mean Absolute Error, Post-1990 Mean Absolute Error, and Pearson correlation r across 92 completed 7-year periods) plus historical market turning-point snapshots comparing expected vs. realized 7-year real returns at the 1982 Interest Rate Peak, 2000 Dot-Com Bubble Peak, 2009 Financial Crisis Low, and Live 2026.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "Get 100-Year Historical Backtest Summary",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Returns a plain-English explanation of the 7-year cross-asset valuation mean-reversion and carry methodology, CPI inflation adjustment, the difference between the four S&P 500 valuation baselines (Post-1990 Margin Baseline, 100-Year Baseline, Shiller 10Y Gov Bond Excess CAPE Yield, and Standard Raw CAPE), fixed-income term and credit spread normalization, and the 1928-2026 out-of-sample backtest verification protocol.
| Parameter | Type | Description |
|---|---|---|
| topic | string | Optional specific topic to explain: 'all', 'equities_cape', 'fixed_income_bonds_cash', 'real_vs_nominal_inflation', or 'backtest_1928_2026'. |
{
"name": "explain_methodology",
"title": "Explain Cross-Asset Valuation Methodology",
"description": "Returns a plain-English explanation of the 7-year cross-asset valuation mean-reversion and carry methodology, CPI inflation adjustment, the difference between the four S&P 500 valuation baselines (Post-1990 Margin Baseline, 100-Year Baseline, Shiller 10Y Gov Bond Excess CAPE Yield, and Standard Raw CAPE), fixed-income term and credit spread normalization, and the 1928-2026 out-of-sample backtest verification protocol.",
"inputSchema": {
"type": "object",
"properties": {
"topic": {
"type": "string",
"description": "Optional specific topic to explain: 'all', 'equities_cape', 'fixed_income_bonds_cash', 'real_vs_nominal_inflation', or 'backtest_1928_2026'."
}
}
},
"annotations": {
"title": "Explain Cross-Asset Valuation Methodology",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Logs a request for an asset class, ETF ticker (such as QQQ, TLT, HYG, IWM, VXUS, TIPS, Gold, REITs, international equities, or crypto), custom time horizon (5-year, 10-year, 20-year, 30-year), or portfolio allocation calculator (60/40 portfolio, retirement withdrawal, glidepath) not listed in the 7 core rows, and returns the closest currently available building-block proxy.
| Parameter | Type | Description |
|---|---|---|
| user_context | string | Brief summary of what the user is trying to compare or solve. |
| requested_item * | string | The ticker, asset class, metric, or feature requested (e.g., 'QQQ', 'TLT', 'HYG', '60/40 portfolio', '10-year horizon'). |
{
"name": "request_missing_asset_or_feature",
"title": "Request Missing Asset or Get Building-Block Proxy",
"description": "Logs a request for an asset class, ETF ticker (such as QQQ, TLT, HYG, IWM, VXUS, TIPS, Gold, REITs, international equities, or crypto), custom time horizon (5-year, 10-year, 20-year, 30-year), or portfolio allocation calculator (60/40 portfolio, retirement withdrawal, glidepath) not listed in the 7 core rows, and returns the closest currently available building-block proxy.",
"inputSchema": {
"type": "object",
"required": [
"requested_item"
],
"properties": {
"user_context": {
"type": "string",
"description": "Brief summary of what the user is trying to compare or solve."
},
"requested_item": {
"type": "string",
"description": "The ticker, asset class, metric, or feature requested (e.g., 'QQQ', 'TLT', 'HYG', '60/40 portfolio', '10-year horizon')."
}
}
},
"annotations": {
"title": "Request Missing Asset or Get Building-Block Proxy",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.