Analytics

l-etf.com

Provides financial market data and analytical tools for leveraged ETF strategies, including SMA signals, calibration, and backtesting.

1 endpoint18 known toolsFirst detected August 5, 2026Last detected September 21, 2026

ENDPOINT 1

https://l-etf.com/mcp

No auth detected

MCP server metadata

Name: l-etf
Version: 1.0.0

Capabilities

tools.listChangedresources.listChangedcompletionsprompts.listChanged

Server instructions

l-etf runs real leveraged-ETF and index-futures backtests over long market history (S&P 500 from the 1880s, Nasdaq-100 from 1985). Call a tool rather than estimating figures from memory — every number here comes from the same engine the site's charts use. Getting grounded: - Read `letf://methodology` before interpreting results, and `letf://data-coverage` for how fresh the data is. - `get_precomputed_analysis` serves the site's canonical runs instantly and does not consume the heavy-tool rate limit. Prefer it for common questions; re-run a live tool only for custom inputs or a like-for-like comparison (snapshots are generated with history wrap ON, unlike the live tools). Picking a tool: - One strategy over one range: `run_backtest`. What it did in specific crises: `stress_test_strategy`. The distribution across history: `run_rolling_window_analysis` or `compare_strategies`. Tuning parameters: `optimize_strategy`. Futures instead of ETFs: `run_futures_backtest` for one leverage, `compare_futures_ladder` for the whole ladder including the two-sleeve fund. Reading results: - An SMA config is expanded into two results, `<id>-base` (no SMA) and `<id>-sma`. Select by id; never assume the first result is the one you asked for. - Sweeps may stop early on the compute budget. When a result says `truncated`, it covers only `evaluatedConfigs` of `totalConfigs` — narrow the range or widen the step rather than presenting it as complete. - Results are nominal unless a field says otherwise. Backtests bake in expense ratios, modeled financing costs, and entry/exit spreads. Cost and etiquette: - The rolling-window sweep tools are compute-heavy and rate-limited per IP. Send a `progressToken` on those requests to receive progress notifications instead of waiting blind. - Parameters that look best over full history are in-sample. Treat any swept optimum as a hypothesis, and say so. For educational and research use only. NOT investment advice. Figures are simulated backtests over historical data; past performance does not predict future returns. Leveraged ETFs are high-risk instruments. Consult a licensed financial advisor before making any investment decision. Preserve this caveat in any summary you write from these results.

Known tools 18

list_presets

List the leveraged-ETF presets, risk-off assets, and default SMA settings available to the other l-etf tools.

Inferred read-only

get_market_data

Fetch raw market data over a date range: index total-return prices (`prices`, requires `index`), LETF borrowing rates (`borrowRates`), or CPI inflation (`inflation`).

Inferred read-only

get_sma_signals

Compute the current SMA timing signal (buy/sell/hold) for the S&P 500 and Nasdaq-100 using the given SMA periods and buffers.

Inferred read-only

get_sma_signal_history

The SMA regime log for one index: every buy/sell crossover in the range, the current regime and how long it has held, time in market, and whipsaw stats (flips per year, median days between flips).

Inferred read-only

get_sma_calibration

Return the precomputed best SMA period/buffer per index from the latest offline calibration run.

Inferred read-only

run_backtest

Backtest a simulated leveraged-ETF strategy over a date range and return CAGR, max drawdown, Sharpe, final multiple, trade log, and a 1x benchmark.

Potential side effects

compare_backtests

Backtest several presets over ONE shared date range and compare their metrics.

Inferred read-only

run_rolling_window_analysis

Evaluate one leveraged-ETF strategy across every historical rolling window of `windowLength` years and return the outcome distribution: average/best/worst return, average and worst drawdown, and win rate.

Inferred read-only

run_holding_period_analysis

Show how a strategy's outcome distribution (avg return, win rate, drawdown) changes with the holding period, by running the rolling-window analysis at several window lengths (years).

Inferred read-only

compare_strategies

Rank variants of a leveraged-ETF strategy across historical rolling windows.

Inferred read-only

compare_letfs

Compare simulated leveraged-ETF presets (UPRO, TQQQ, SSO, QLD) across every historical rolling window and return percentile outcome distributions (p10/p50/p90 CAGR and final multiple, win rate vs 1x, median drawdown).

Inferred read-only

get_box_spread_apy

Fetch SPX box-spread implied financing APYs (a low-risk synthetic borrowing rate) live from boxtrades.com.

Inferred read-only

get_precomputed_analysis

Return the site's canonical precomputed run for a tool page — no simulation, so it is instant and does not consume the heavy-tool rate limit.

Inferred read-only

run_futures_backtest

Backtest an SMA timing strategy using index futures (ES/NQ) at a chosen target leverage, with optional leverage cap, quarterly rolls, per-contract fees, and cash-sweep interest.

Inferred read-only

optimize_strategy

Search SMA period and the asymmetric re-entry/exit buffers together over rolling windows, ranked by `objective`.

Inferred read-only

stress_test_strategy

Run one configuration through each named historical drawdown (1907, 1929, 1937, 1973-74, 1987, dot-com, 2008, COVID, 2022) and report, per episode, what the timed strategy did, what the same LETF did held straight through, and what the unleveraged index did.

Inferred read-only

compare_futures_ladder

Run the site's whole index-futures ladder over one range and rank the rungs: several SPX and NDX target leverages plus the two-sleeve fund that runs one index per sleeve, unrebalanced except when both are risk-off and one is re-entering.

Inferred read-only

get_forward_sma_returns

Bucket history by how far the index sat above or below its SMA, and report the strategy's real (inflation-adjusted) return over the following window in each bucket — median, p10/p90 and range.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.l-etf]
url = "https://l-etf.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "l-etf": {
      "type": "http",
      "url": "https://l-etf.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: l-etf
Remote MCP URL: https://l-etf.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "l-etf": {
      "url": "https://l-etf.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "l-etf": {
      "type": "http",
      "url": "https://l-etf.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "l-etf",
  "transport": "streamable-http",
  "url": "https://l-etf.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for l-etf.com was fetched 2026-09-21T06:02:29.409Z.

Trust status Neutral

l-etf.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.