I connected VS Code Copilot to a trading API and tested a SPY put spread

Follow this worked strategy

I connected VS Code Copilot to the NexusTrade trading API and had it research a SPY bear put spread, build the spread rules, and inspect the completed 2024 test. The agent operated this workflow through NexusTrade's MCP server; it did not build the integration. The spread lost 13.34% against full-capital SPY at 25.30%, including a recorded trade that lost $487.82. This is a development test on examined dates. Judge frozen rules on dates you have not used yet.

Follow the full journey

Step 1 of 6

Connect VS Code Copilot

Add the NexusTrade server

.vscode/mcp.json

Copy configuration

{
  "servers": {
    "nexustrade": {
      "type": "http",
      "url": "https://nexustrade.io/api/mcp"
    }
  }
}

Scroll horizontally to read the full command, or copy it.

Open the Command Palette with Cmd+Shift+P on macOS or Ctrl+Shift+P on Windows/Linux. Run MCP: Add Server and follow the remote HTTP server flow with the URL shown above and name nexustrade. Choose workspace .mcp.json or Copilot Global for a new portable configuration.

Sign in to your NexusTrade account

Alternatively, run MCP: Open User Configuration and merge the servers configuration shown above into that VS Code profile file. It is the VS Code profile format, rather than the portable mcpServers format. Run MCP: List Servers, select NexusTrade and start it. Complete the account sign-in requested by the connection, then inspect its tools in chat. Workspace trust and server enablement can affect availability.

What you should see

The result identifies Apple's company filing, filing date and source URL. The connection check makes no account changes.

Copy connection check for VS Code Copilot

Inspect the request

Use NexusTrade’s sec_edgar tool with action list_filings, ticker AAPL and limit 1. Report the company, filing form, filing date and source URL from the result. Use only this public read. Do not access portfolios, ingest filings, create resources or make changes. If the tool is unavailable, say so.

Step 2 of 6

Research SPY and the put spread

Read the SPY underlying, option expiry and strike selectors together. The long and short put legs use the same expiry; inspect the actual selected contracts before reviewing the debit and collateral.

What you should see

A dated brief names the instrument, original sources and assumptions that matter to this strategy.

Copy prompt for VS Code CopilotOpen in Aurora →

Inspect the request

Research a SPY bear put spread. Explain the underlying, 100-share contract multiplier, long and short legs, expiry, debit, maximum loss and capped gain. Use original instrument and option sources. Separate expiration payoff from mark-to-market history. Keep this read-only.

Step 3 of 6

Build the SPY put spread

Enter when SPY is below its 50-day average and no matching option position is open. Review both legs and the signal and 14-DTE exits before saving.

Entry

SPY < SMA50; matching position count = 0

Legs

Buy ATM put; sell put at -5% strike

Expiry

Nearest available expiry 30 to 45 days away; ratios 1:1

Sizing

One strategy unit; collateral and liquidity apply

Exit

SPY >= SMA50 or at most 14 DTE

What you should see

The preview shows three rules, both contract selectors and the exact sizing method.

Copy prompt for VS Code CopilotOpen in Aurora →

Inspect the request

Use build_portfolio to preview this exact SPY bear put spread configuration. Show the entry, sizing, exits, valid and issues. After I approve the rules, use create_portfolio once to save a new draft, then read it back and retain its returned ID. Keep this candidate separate from published research portfolios. Stop before submitting a paid test or deploying. { "name": "Public SEO example - Bear put spread", "initialValue": 10000, "cash": 10000, "buyingPower": 10000, "strategies": [ { "name": "Open Bear put spread", "condition": { "type": "And", "conditions": [ { "type": "Base", "lhs": { "type": "Price", "targetAsset": { "type": "Stock", "symbol": "SPY", "name": "SPY" } }, "comparison": "lessThan", "rhs": { "type": "SimpleMovingAverage", "targetAsset": { "type": "Stock", "symbol": "SPY", "name": "SPY" }, "window": { "length": 50, "interval": "Day" } } }, { "type": "Base", "lhs": { "type": "OptionPositionCount", "underlying": "SPY", "optionType": "put", "direction": "long", "spreadType": "vertical" }, "comparison": "equal", "rhs": { "type": "Value", "value": 0 } } ] }, "action": { "type": "OpenOption", "builder": { "legs": [ { "optionType": "put", "direction": "long", "expirationSelector": { "minDaysToExpiration": 30, "maxDaysToExpiration": 45, "preference": "nearest" }, "strikeSelector": { "distanceType": "percent", "distance": 0 }, "ratio": 1 }, { "optionType": "put", "direction": "short", "expirationSelector": { "minDaysToExpiration": 30, "maxDaysToExpiration": 45, "preference": "nearest" }, "strikeSelector": { "distanceType": "percent", "distance": 5 }, "ratio": 1 } ], "underlyingSymbol": "SPY", "spreadType": "vertical" }, "allocation": { "type": "contracts", "amount": 1 } }, "orderExecution": { "type": "Market" } }, { "name": "Close when signal invalidates", "condition": { "type": "Base", "lhs": { "type": "Price", "targetAsset": { "type": "Stock", "symbol": "SPY", "name": "SPY" } }, "comparison": "greaterThanOrEqual", "rhs": { "type": "SimpleMovingAverage", "targetAsset": { "type": "Stock", "symbol": "SPY", "name": "SPY" }, "window": { "length": 50, "interval": "Day" } } }, "action": { "type": "CloseOption", "underlyings": [ "SPY" ], "spreadType": "vertical", "closeScope": "spread", "quantity": { "type": "all" } }, "orderExecution": { "type": "Market" } }, { "name": "Close at 14 DTE", "condition": { "type": "Base", "lhs": { "type": "Value", "value": 1 }, "comparison": "greaterThan", "rhs": { "type": "Value", "value": 0 } }, "action": { "type": "CloseOption", "underlyings": [ "SPY" ], "spreadType": "vertical", "closeScope": "spread", "triggers": [ { "type": "dte", "maxDte": 14 } ], "quantity": { "type": "all" } }, "orderExecution": { "type": "Market" } } ], "supportsFractionalShares": false, "alertsEnabled": false, "dividendPolicy": "cash" }

Bear put spread 2024-12-31, 21:00:00 UTC

8,665.52

Full-capital SPY buy and hold 2024-12-31, 21:00:00 UTC

12,530.29

Bear put spreadFull-capital SPY buy and holdHistorical simulation

Step 4 of 6

Inspect the completed 2024 spread test

Compare the spread curve with full-capital SPY over the same year. Option contract selection and execution assumptions belong to this result.

Return

-13.34%

SPY buy and hold

25.30%

Max drawdown

23.74%

Closed option legs

16

Commissions

$22.10

What you should see

The bear put spread returned -13.34% in this completed historical simulation.

Copy prompt for VS Code CopilotOpen in Aurora →

Inspect the request

Prepare a backtest of my reviewed SPY bear put spread draft for 2024-01-01 through 2024-12-31 with $10,000 and SPY baseline. Preserve the saved selectors and sizing. Match $0.65 commission per contract and slippage of 0.5 of half-spread. Show the request and estimated cost before submission. Inspect the returned history, selected contracts, collateral, quote timing and synthetic quote usage; compare exposure with full-capital SPY.

Step 5 of 6

Observe SPY bear put spread in paper trading

Keep the selectors and sizing fixed in a separate paper portfolio. Inspect the long and short legs as one spread, with matching expiries and the exits defined above.

Inspect before accepting an order

The selected SPY strikes, matching expiry, contract quantities, debit, collateral, pending order legs and 14-DTE exit.

What you should see

Your paper portfolio has its own ID, start date, schedule and dated history. These forward observations begin with your own run.

Copy prompt for VS Code CopilotOpen in Aurora →

Inspect the request

Read back the reviewed SPY bear put spread draft. Prepare a separate paper-only deployment with the same rules and $10,000 starting capital. Show the plan for approval. Retain the resulting paper ID and verify its deployment type, timing, pending simulated orders and actual history. Inspect: The selected SPY strikes, matching expiry, contract quantities, debit, collateral, pending order legs and 14-DTE exit. Keep the rules fixed and brokerage accounts unchanged.

Step 6 of 6

Review SPY bear put spread for live deployment

Review the spread in the target account only after confirming that its broker connection supports the required multi-leg option actions and your account has the necessary options permissions.

Open the live deployment walkthrough →

Account and instrument review

SPY multi-leg options support, account permission level, debit and collateral, quote availability, both leg quantities and exit support.

What you should see

The review identifies the target account, supported instruments, rule changes and approval settings before confirmation.

Copy prompt for VS Code CopilotOpen in Aurora →

Inspect the request

Prepare a live deployment review for my SPY bear put spread paper portfolio. Read the actual account and broker capabilities, incoming rules and any existing rules that would be disabled. Check: SPY multi-leg options support, account permission level, debit and collateral, quote availability, both leg quantities and exit support. Show the plan and keep live trading unchanged until I explicitly confirm it. If an instrument or action is unsupported, report it and stop.

Follow the VS Code Copilot session

{
  "servers": {
    "nexustrade": {
      "type": "http",
      "url": "https://nexustrade.io/api/mcp"
    }
  }
}

This guide runs on NexusTrade's MCP server. VS Code Copilot operated the trading workflow below, from connection to the live review. The agent's role here is operating the workflow through that server.

The table names the tool call, the approval checkpoint, and the artifact to keep at each stage. Placeholders such as a returned draft ID stand for values your own run returns. This page records no IDs from anyone else's run.

The recorded anchor is the completed 2024 spread test below, including the recorded trade that lost $487.82 and the largest decline in the exported history.

Where VS Code Copilot stops for approval

Each consequential action in this guide waits at an approval gate. The agent previews first and acts only after explicit approval.

The rules preview returns valid and issues before anything is saved. The agent resolves problems and re-previews instead of saving a candidate with open problems.

1. Approve the rules before the agent saves them

   The agent previews the configuration with build_portfolio and shows entry, sizing, exits, valid, and issues. It saves with create_portfolio only after approval and reads the returned draft back.

2. Approve the test cost before the agent submits once

   Historical tests are paid runs. The agent shows the exact request and estimated cost for approval before submitting once, then polls the same returned test ID until complete.

3. Approve the paper plan and verify it is paper

   The paper deployment is a separate portfolio with its own ID. The agent shows the plan for approval, verifies the deployment type, and leaves brokerage accounts unchanged.

4. Confirm the live move explicitly, or nothing moves

   The agent reads the actual account and broker capabilities first and keeps live trading unchanged until explicit confirmation. It reports an unsupported instrument or action and stops.

Inspect the spread execution assumptions

Follow the recorded put trade

Continue exploring