Stratify

Describe a strategy. Test it.

Stratify backtests Indian index option strategies on a year of real 1-minute NIFTY options data. Describe the trade in plain words — the legs, when to enter, how to manage it while it is open — and the server runs it against every trading day in the window and returns what actually happened.

What you can ask

Backtest a weekly 20-delta NIFTY strangle at 09:30, 4 days to expiry, stop at a 100% loss of credit, target 60%.
Example path

MCP connector

Server URL: https://stratify-mcp.aeon-labs.site/mcp
Login: OAuth
Protocol: MCP 2025-06-18 · Interactive UI
Instructions: Backtesting for Indian index options on real 1-minute NIFTY and SENSEX data. The two are different contracts: SENSEX trades a 100-point strike grid against NIFTY's 50, and its options begin 2023-08-07, so a percent-offset or an entry_dte reasoned about on one is not automatically right on the other. Call for the window per symbol. Results are computed server-side. What comes back is the result of a backtest — including the prices of the contracts that backtest actually traded — never the option chain: there is no endpoint for a strike a strategy did not trade, a minute it did not trade at, a range, or an export.
Two cadences, which answer different questions: cadence 'weekly' (default) enters once per expiry, on the day matching entry_dte — about 58 trades a year. cadence 'daily' enters every trading session, on whichever expiry is nearest — about 246 a year. This is the one that matches a description like "every day". exit_time sets a clock exit that squares the position off in the same session, so "buy at 11, sell at 2, every day" is cadence 'daily', entry_time '11:00', exit_time '14:00'. Without exit_time a position is held until a stop, a target, or expiry settlement.
Every backtest result includes a report_url: a shareable page carrying the equity curve, the honesty panel and the trade table. creates that page for a stored backtest and returns its URL.
reports the exact window, lot sizes and structures available to this key, which change between tiers and over time. describes how a result is produced and what each check can and cannot establish.
Backtest results are saved to the user's account. returns the ones that passed the out-of-sample and walk-forward checks, ranked by worst walk-forward fold rather than by P&L, because total return is what a parameter sweep maximises by construction.
Five things about this market are commonly assumed wrong, and each one changes the numbers:
NIFTY weekly expiry is TUESDAY for most of this window, not Thursday. It changed around 2025-09-02. Holidays shift it earlier.
The lot size is not constant. It is 75 for expiries through 2025-12-30 and 65 from 2026-01-06. Every rupee figure depends on which regime a trade fell in.

Tools

Reads data8

Changes data3

Skills

None in the store listings or on the server

What you can ask

Backtest a weekly 20-delta NIFTY strangle at 09:30, 4 days to expiry, stop at a 100% loss of credit, target 60%.

Example path

MCP connector

Server URL

https://stratify-mcp.aeon-labs.site/mcp

OAuth

Protocol

MCP 2025-06-18 · Interactive UI

Instructions

Backtesting for Indian index options on real 1-minute NIFTY and SENSEX data. The two are different contracts: SENSEX trades a 100-point strike grid against NIFTY's 50, and its options begin 2023-08-07, so a percent-offset or an entry_dte reasoned about on one is not automatically right on the other. Call for the window per symbol. Results are computed server-side. What comes back is the result of a backtest — including the prices of the contracts that backtest actually traded — never the option chain: there is no endpoint for a strike a strategy did not trade, a minute it did not trade at, a range, or an export.

Two cadences, which answer different questions: cadence 'weekly' (default) enters once per expiry, on the day matching entry_dte — about 58 trades a year. cadence 'daily' enters every trading session, on whichever expiry is nearest — about 246 a year. This is the one that matches a description like "every day". exit_time sets a clock exit that squares the position off in the same session, so "buy at 11, sell at 2, every day" is cadence 'daily', entry_time '11:00', exit_time '14:00'. Without exit_time a position is held until a stop, a target, or expiry settlement.

Every backtest result includes a report_url: a shareable page carrying the equity curve, the honesty panel and the trade table. creates that page for a stored backtest and returns its URL.

reports the exact window, lot sizes and structures available to this key, which change between tiers and over time. describes how a result is produced and what each check can and cannot establish.

Backtest results are saved to the user's account. returns the ones that passed the out-of-sample and walk-forward checks, ranked by worst walk-forward fold rather than by P&L, because total return is what a parameter sweep maximises by construction.

Five things about this market are commonly assumed wrong, and each one changes the numbers:

NIFTY weekly expiry is TUESDAY for most of this window, not Thursday. It changed around 2025-09-02. Holidays shift it earlier.

The lot size is not constant. It is 75 for expiries through 2025-12-30 and 65 from 2026-01-06. Every rupee figure depends on which regime a trade fell in.