How to connect Grok Bot to NexusTrade

Add a bot, ask a question. That is the whole setup.

Connect NexusTrade to this task

Open Connect apps in Grok Bot’s sidebar. If NexusTrade is listed, choose Add, complete browser sign-in and attach it with @ in this task. For an existing custom MCP connection, use the endpoint shown here.

What you should see: NexusTrade tools are available to the task after authentication. The rendition above shows the documented setup, not verification of your account.

https://nexustrade.io/api/mcp

Check that the connected account is yours

Ask for fetch_portfolios with the arguments below. Match a returned portfolio’s name and type to your NexusTrade account. For its full rules, pass the returned portfolioId as portfolio_id to get_portfolio.

What you should see: The returned books belong to your intended account. An authenticated empty list is valid for a new account. This check only reads records.

Returned field

portfolioId identifies one book; page through the list before declaring it absent.

Read-back check

Match portfolio.portfolioId, portfolio.type and portfolio.strategies.

{
  "include_live": false,
  "include_paper": true,
  "include_chat_portfolios": true,
  "include_inactive": true,
  "include_positions": false,
  "limit": 50,
  "page": 1
}

Use the worked NVDA company question

Open the NVDA guide and use its dated company question. Compare operating income with revenue for the same quarter, then keep the filing link with the calculation.

What you should see: The recorded NexusTrade example below gives $63.734 billion ÷ $96.221 billion = 66.24%. It describes operating profitability for that quarter, not a forecast or a new Grok Bot run.

Recorded reporting period

NVDA Q2 fiscal 2027 · quarter ended July 26, 2026 · filed August 26, 2026.

Company revenue

$96.221 billion

Operating income

$63.734 billion

What the original Grok Bot experiment shows

The August 2026 case study records MCP and Python SDK strategy work, followed by a human-directed redesign and manual approval. Its historical tests, paper reproductions and funded account are separate records.

Choose a different task

These are separate guides, not three consecutive steps: inspect a company brief, review a fixed historical candidate, or prepare a forward paper observation.

If authentication needs a handoff or the connector is unavailable

For sign-in or two-factor authentication, open Agent Computer, take control, finish the requested step and return control. Grok Bot’s connected apps are shared across your Bots.

If the connector cannot finish authentication, use the documented Python SDK in the Bot’s terminal with its API key configured through the secret environment. SDK credentials and MCP OAuth are separate.

Leave a record the next session can use

Keep the research question, primary source links, selected universe, rejected candidates and accepted backtest IDs in the Bot workspace. Ask it to check current sources when resuming the task. A remembered thesis may be stale even when the files persist.

A persistent agent with a real workspace

Grok Bot is the agent product with a persistent cloud computer, browser, filesystem and terminal. That workspace can retain a research brief and strategy artifacts across tasks. Its ability to use a terminal makes the Python SDK a practical companion to the account tool connection.

Use a named research assignment with explicit outputs: source notes, a frozen universe, the complete strategy configuration and the returned operation IDs. Keep account access and approval choices deliberate.

The tool sequence

Inspect the discovered inputs before submitting a call. For a new candidate, validate and save it first; for a saved candidate, start with get_portfolio. Record the portfolio and backtest identifiers returned by the account tools.

Hand the Bot a research protocol

State the thesis, instrument universe, dates, baseline, fees and maximum candidate budget before testing. Require a frozen historical test window and source availability dates. Ask the Bot to report rejected candidates rather than hiding the selection process.

Research this thesis using dated primary sources. Freeze the candidate universe and write explicit entry, sizing and exit rules. Show the experiment plan before running compute. Keep historical validation and future paper observation separate, preserve every accepted operation ID, and stop before deployment or brokerage approval.

Review before deployment

The case study’s practical lesson is that attractive historical totals did not settle the allocation design. Inspect the portfolio’s actual configuration, exposure and exits before accepting a candidate.

Use a new paper deployment to observe forward simulated behavior. Existing brokerage portfolios and any staged orders require their own explicit review. A persistent workspace does not supply approval for brokerage actions.

Review a brokerage deployment separately

Public and Tradier have native NexusTrade account connection and strategy-port flows described below. Public also offers its own external MCP route. The Robinhood guide uses Claude Code with separate NexusTrade and Robinhood MCP servers; it does not imply that this client already has a verified native Robinhood connection. Broker account selection, order approval and a verified stop remain separate from paper observation.

Continue exploring