I connected Meta Muse to a trading API and tested an ETH rule

Follow this worked strategy

I connected Meta Muse to the NexusTrade trading API and had it research ETH-USD and test a Bollinger mean-reversion rule across the completed 2024 run. The agent operated this workflow through NexusTrade's MCP server; it did not build the integration. The rule lost 9.42% against SPY at 25.30%, with $837.50 in recorded fees. 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 Meta Muse

Connect Meta Muse in the intended environment

Meta Muse MCP configuration

Copy setup text

Create a Custom Connector named NexusTrade. Use the remote Streamable HTTP MCP endpoint https://nexustrade.io/api/mcp. Read the server authentication discovery and tool schemas. Guide me through NexusTrade sign-in and list the available tools. Do not place orders, activate portfolios, run backtests or change account settings.

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

Open Muse and send the Custom Connector request below. Review the proposed NexusTrade endpoint and tools, then finish NexusTrade sign-in using the private authentication flow. Muse Code has a separate setup; this path is for the Muse personal agent.

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 Meta Muse

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 ETH-USD and its trading calendar

Inspect the spot pair, source timestamps and fee model. This strategy evaluates daily indicators while crypto prices also move on weekends.

What you should see

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

Copy prompt for Meta MuseOpen in Aurora →

Inspect the request

Research ETH-USD for this spot-only ETH Bollinger mean reversion example. Report the asset, quoted currency, spot versus derivative distinction, trading calendar and price-source timestamps. Use original market and instrument sources. Check exchange or broker pair support separately from the historical model.

Step 3 of 6

Preview the ETH Bollinger mean reversion rules

Keep the exact daily indicator thresholds and flat-position guard shown here. Allocate 95% of buying power on entry and close all held units when the exit fires.

Entry

Saved rule: Price < BollingerBand(20, Day, -2) AND position value = 0

Exit

Saved rule: Price >= SMA(20, Day) AND position value > 0

Allocation

Saved rule: 95% of buying power per entry; sell 100% of held units on exit

Pair

Saved rule: ETH-USD

What you should see

The preview resolves this specific pair, entry, exit and fractional spot sizing.

Copy prompt for Meta MuseOpen in Aurora →

Inspect the request

Use build_portfolio to preview this exact ETH Bollinger mean reversion 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 crypto example - ETH Bollinger mean reversion", "initialValue": 10000, "cash": 10000, "buyingPower": 10000, "strategies": [ { "name": "Enter ETH Bollinger mean reversion", "condition": { "type": "And", "conditions": [ { "type": "Base", "lhs": { "type": "Price", "targetAsset": { "type": "Cryptocurrency", "symbol": "ETH-USD", "name": "ETH-USD" } }, "comparison": "lessThan", "rhs": { "type": "BollingerBand", "targetAsset": { "type": "Cryptocurrency", "symbol": "ETH-USD", "name": "ETH-USD" }, "numStandardDeviations": -2, "window": { "length": 20, "interval": "Day" } } }, { "type": "Base", "lhs": { "type": "PositionValue", "targetAssets": [ { "type": "Cryptocurrency", "symbol": "ETH-USD", "name": "ETH-USD" } ] }, "comparison": "equal", "rhs": { "type": "Value", "value": 0 } } ] }, "action": { "type": "Buy", "targetAsset": { "type": "Cryptocurrency", "symbol": "ETH-USD", "name": "ETH-USD" }, "amount": { "type": "percent of buying power", "amount": 95 } }, "orderExecution": { "type": "Market" } }, { "name": "Exit ETH Bollinger mean reversion", "condition": { "type": "And", "conditions": [ { "type": "Base", "lhs": { "type": "Price", "targetAsset": { "type": "Cryptocurrency", "symbol": "ETH-USD", "name": "ETH-USD" } }, "comparison": "greaterThanOrEqual", "rhs": { "type": "SimpleMovingAverage", "targetAsset": { "type": "Cryptocurrency", "symbol": "ETH-USD", "name": "ETH-USD" }, "window": { "length": 20, "interval": "Day" } } }, { "type": "Base", "lhs": { "type": "PositionValue", "targetAssets": [ { "type": "Cryptocurrency", "symbol": "ETH-USD", "name": "ETH-USD" } ] }, "comparison": "greaterThan", "rhs": { "type": "Value", "value": 0 } } ] }, "action": { "type": "Sell", "targetAsset": { "type": "Cryptocurrency", "symbol": "ETH-USD", "name": "ETH-USD" }, "amount": { "type": "percent of current positions", "amount": 100 } }, "orderExecution": { "type": "Market" } } ], "supportsFractionalShares": true, "supportsCrypto": true, "alertsEnabled": false, "dividendPolicy": "cash" }

ETH Bollinger mean reversion 2024-12-31, 21:00:00 UTC

9,058.18

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

12,530.29

BTC buy and hold 2024-12-31, 21:00:00 UTC

21,926.92

ETH Bollinger mean reversionSPY buy and holdBTC buy and holdHistorical simulation

Step 4 of 6

Inspect the completed ETH-USD test

Read this strategy curve alongside the full-capital SPY and BTC comparisons. The 0.7% fee on each fill is part of the recorded result.

Backtest return

-9.42%

Reported maximum drawdown

28.52%

Total recorded trading fees

$837.50

Ending portfolio value

$9058.18

What you should see

The completed 2024 ETH Bollinger mean reversion simulation returned -9.42% with reported maximum drawdown 28.52%.

Copy prompt for Meta MuseOpen in Aurora →

Inspect the request

Prepare a daily 2024-01-01 through 2024-12-31 backtest of my exact ETH Bollinger mean reversion draft with $10,000, fractional spot units and the saved allocation. Preserve the 0.7% crypto fee per traded notional on every fill. Show the request and estimated cost before submission. Inspect the same returned test ID, pair-specific entry and exit events, cash, position values and full-capital SPY/BTC comparisons.

Step 5 of 6

Observe ETH Bollinger mean reversion in paper trading

Observe the ETH-USD rule prospectively with fractional spot units. Keep its daily indicator window and 95% entry allocation while recording weekend evaluations.

Inspect before accepting an order

The ETH-USD signal, spot units, fee, cash balance, flat-position guard, daily evaluation schedule and weekend behavior.

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 Meta MuseOpen in Aurora →

Inspect the request

Read back the reviewed ETH Bollinger mean reversion 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 ETH-USD signal, spot units, fee, cash balance, flat-position guard, daily evaluation schedule and weekend behavior. Keep the rules fixed and brokerage accounts unchanged.

Step 6 of 6

Review ETH Bollinger mean reversion for live deployment

Check the actual connection for this specific spot pair before preparing a live move. Review venue support, pair naming, minimum order size and its operating calendar.

Open the live deployment walkthrough →

Account and instrument review

ETH-USD spot support, fractional units, minimum order size, venue fees, weekend timing and exits; stop if the pair is unsupported.

What you should see

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

Copy prompt for Meta MuseOpen in Aurora →

Inspect the request

Prepare a live deployment review for my ETH Bollinger mean reversion paper portfolio. Read the actual account and broker capabilities, incoming rules and any existing rules that would be disabled. Check: ETH-USD spot support, fractional units, minimum order size, venue fees, weekend timing and exits; stop if the pair is unsupported. 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 Meta Muse session

Create a Custom Connector named NexusTrade. Use the remote Streamable HTTP MCP endpoint https://nexustrade.io/api/mcp. Read the server authentication discovery and tool schemas. Guide me through NexusTrade sign-in and list the available tools. Do not place orders, activate portfolios, run backtests or change account settings.

This guide runs on NexusTrade's MCP server. Meta Muse 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 test below. It lost 9.42% against SPY at 25.30%, with $837.50 in recorded fees.

Where Meta Muse 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 captured ETH-USD measurements

Inspect the recorded trades

Inspect the original signal record

{
  "eventType": "BuySignal",
  "event": {
    "eventType": "BuySignal",
    "timestamp": "2024-12-19T21:00:00.000Z",
    "signals": [
      {
        "conditionName": "ETH-USD last price < 20 Day ETH-USD Bollinger Band and Position market value (ETH-USD) = Constant 0",
        "audit": {
          "type": "minimal",
          "results": {
            "0.0": {
              "isTrue": true,
              "lhsValue": 3366.02001953125,
              "rhsValue": 3513.2366040393435,
              "lhsError": null,
              "rhsError": null,
              "comparison": "lessThan"
            },
            "0.1": {
              "isTrue": true,
              "lhsValue": 0,
              "rhsValue": 0,
              "lhsError": null,
              "rhsError": null,
              "comparison": "equal"
            }
          },
          "failuresOnly": false
        },
        "isTrue": true,
        "actionName": "Buy",
        "actionMetadata": {
          "buyOrSell": {
            "targetAsset": {
              "name": "ETH-USD",
              "symbol": "ETH-USD",
              "type": "Cryptocurrency",
              "underlyingSymbol": null,
              "optionType": null,
              "expirationDate": null,
              "strikePrice": null,
              "multiplier": null
            },
            "allocation": {
              "type": "percent of buying power",
              "amount": 95
            },
            "price": 3366.02001953125,
            "orderType": "Market Order"
          }
        },
        "orderExecution": {
          "type": "Market"
        }
      }
    ]
  },
  "timestamp": 1734642000000
}

Continue exploring