Stratify
site.aeon-labs/stratifyBacktest NIFTY option strategies on real 1-minute data, with an honest out-of-sample panel.
Score: 100/100
Handshake verified by our own probe.
Tools · 11
Backtest an Indian index option strategy on real 1-minute NIFTY options data. Returns P&L after real charges and slippage, return-on-margin, and an honesty panel: out-of-sample split, walk-forward fol…
What data is available: symbols, date range, resolution, structures, gates, biases, the cost model, and every known gap.
How a result is produced: entry pricing, settlement, margin, slippage, the honesty rubric, and what each check can and cannot establish.
The account's backtests, newest first, with id, date, trade count, net P&L and report URL. Answers a request for the most recent run, which list_strategies does not: that one returns only results that…
Retrieve a previous backtest result by its id — honesty panel, equity curve and per-trade detail, exactly as first computed.
Strategies from THIS account's history that held up under out-of-sample and walk-forward checks, not merely ones that made money. Ranked by worst walk-forward fold — consistency, not size. Answers wha…
Search what this service covers — symbols, dates, structures, signals, methodology. Returns ids usable with fetch.
Fetch a document or backtest result by id, as returned by search.
Files a bug report or feature request when the user asks to report something. Confirm the title and body with the user before filing. Passing backtest_id attaches that backtest's spec so the issue can…
Creates a shareable report page for a backtest the user owns and returns its URL. The page carries the honesty panel, equity and drawdown curves, walk-forward folds, the gross-to-net breakdown, a mont…
Reports this account has filed, and where each one stands. Use it to answer 'did that bug I reported ever get fixed?'.
Resources · 17
WHY THIS TOPIC EXISTS.
stratify://knowledge/changelog
A CYCLE is one opened position.
stratify://knowledge/overview
HOW TO EXPRESS AN INTRADAY STRATEGY, and what changes when you do.
stratify://knowledge/intraday
WHAT IS REMEMBERED, AND WHAT COUNTS AS GOOD.
stratify://knowledge/strategy_book
WHAT LEAVES THIS SERVICE, stated exactly, because 'no data is returned' was true of v1 and is no longer the whole truth.
stratify://knowledge/what_is_returned
MEASURED FROM THE SERVED DATA, and the three most common wrong assumptions.
stratify://knowledge/contract_spec
Zerodha 2026 rates, verified: Rs 20 per order per leg, STT 0.
stratify://knowledge/costs
Defined-risk combos are EXACT — margin is the maximum loss, which is what SPAN recognises for a hedged position.
stratify://knowledge/margin
Modelled, not measured, and the difference matters.
stratify://knowledge/slippage
58 % of contract-minutes have no volume at all, which is normal for an option chain and the reason entry requires a real print.
stratify://knowledge/liquidity
Five ship in v1, and they fail in different ways.
stratify://knowledge/structures
Out-of-sample is a chronological 70/30 split, never random — a random split over overlapping weekly cycles leaks the future into the past.
stratify://knowledge/validation
THE BINDING CONSTRAINT, and the one most often ignored.
stratify://knowledge/sample_size
The danger is not one bad backtest, it is the search.
stratify://knowledge/overfitting
What the numbers can and cannot carry.
stratify://knowledge/interpreting_results
Observed repeatedly, in this order of frequency.
stratify://knowledge/common_mistakes
Inline chart view for a backtest result: verdict, headline numbers, equity and drawdown, walk-forward folds, and the evidence summary. Expands to add the month grid and the cost breakdown.
ui://stratify/backtest
Prompts · 3
Run a strategy and interpret it with the sample-size and multiple-comparison limits applied. Use this instead of reading a backtest result directly.
Probe a promising result the way a sceptic would: neighbouring parameters, doubled slippage, and the held-out slice.
Translate a backtest into plain language, including what it does not establish. Never phrases it as advice.
How to use
Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://stratify-mcp.aeon-labs.site/mcp
Cursor or Cline: add to your MCP config:
{
"mcpServers": {
"stratify": {
"url": "https://stratify-mcp.aeon-labs.site/mcp",
"transport": "streamable-http"
}
}
}