cd /news/ai-agents/questrade-connects-brokerage-account… · home topics ai-agents article
[ARTICLE · art-81188] src=letsdatascience.com ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Questrade Connects Brokerage Accounts to Claude Through MCP

Questrade unveiled an MCP connection and conditional trade automation at a July 29 product showcase in Toronto, allowing customers to connect brokerage accounts to Claude or Claude Code for portfolio queries and order drafting, with trade execution requiring approval in the Questrade app. The company claims it is the first Canadian financial institution to offer agentic-finance features, though supported agents are currently limited to Claude and Claude Code, with ChatGPT and others listed as coming soon.

read3 min views1 publishedJul 30, 2026
Questrade Connects Brokerage Accounts to Claude Through MCP
Image: Letsdatascience (auto-discovered)

Questrade unveiled an MCP connection and conditional trade automation at a July 29 product showcase in Toronto. Its current guide says customers can connect accounts to Claude or Claude Code, query portfolio and market data, and draft orders that require approval in the Questrade app; ChatGPT and other agents are listed as coming soon. A separate Flows feature can execute user-defined trading rules.

Questrade unveiled two agentic-finance features at a July 29 product showcase in Toronto: a Model Context Protocol connection for AI agents and a rules-based trading feature called Flows. The products bring account context and trade workflows closer to conversational interfaces, but they use different execution controls.

Questrade's current setup guide lists Claude and Claude Code as the supported MCP agents. ChatGPT, Cursor, Visual Studio Code with GitHub Copilot Chat, and Codex CLI are marked as coming soon. That current availability is narrower than the broader Claude-and-ChatGPT positioning reported from the showcase.

What the MCP connection can do

The official guide says customers can authorize an agent to read balances, positions, orders, account activity, market quotes, historical prices, and option-chain data. Trade permission is separate from read access. When enabled, an agent can build an order preview, but the customer must approve the instruction through Questrade's mobile app before it reaches the market.

Questrade says the agent cannot skip that preview or independently place, change, or cancel an order. The connection is enforced against permissions granted on Questrade's own login page, so the agent does not receive the customer's Questrade password. Order and activity history exposed through the connection covers the previous 90 days.

The Globe and Mail reported that Questrade presented the release as Canada's first direct brokerage-account connection to popular AI assistants. BetaKit similarly reported that Questrade described itself as the first Canadian financial institution to offer agentic-finance features. Those are company market-position claims, not independently verified rankings.

Flows is a separate automation path

Flows lets Questrade Pro users define conditions that trigger trades. Questrade's product page gives examples such as buying after a specified price decline, investing idle cash above a threshold, or trimming a concentrated position. Some additional templates remain marked as coming soon.

Questrade says Flows execute only against conditions set by the user and can be d. Users can configure notifications and require sign-off before a Flow places a trade. That makes Flows distinct from the MCP workflow: MCP lets an external agent analyze authorized account context and prepare an order for mobile approval, while Flows monitor predefined conditions inside Questrade's platform.

For practitioners building AI interfaces in regulated financial settings, the important design boundary is not whether natural language can describe a trade. It is where authorization is enforced, how permissions separate reading from trading, what data window the agent receives, and whether every proposed action leaves a reviewable audit trail.

Key Points #

  • 1Questrade's current MCP guide supports Claude and Claude Code; ChatGPT and several other agents are listed as coming soon.
  • 2MCP trade instructions require a preview and approval in the Questrade app, with read and trade permissions granted separately.
  • 3Flows is a separate Questrade Pro feature that executes user-defined conditions and can be configured to require sign-off.

Scoring Rationale #

The launch is a concrete MCP deployment in regulated retail brokerage, with explicit permission, approval, and automation boundaries. Its immediate reach remains limited to Questrade and a currently narrow set of supported agents.

Sources #

Primary source and supporting public references used for this report.

Practice with real FinTech & Trading data

90 SQL & Python problems · 15 industry datasets

[Active Verified Users by Income TierEasy](/problems/sql/active-verified-users-by-income)

[Technology Stocks with High BetaMedium](/problems/sql/technology-stocks-with-high-beta)

[Portfolio Performance ScorecardHard](/problems/sql/portfolio-performance-scorecard)

250 free problems · No credit card

See all FinTech & Trading problems

── more in #ai-agents 4 stories · sorted by recency
── more on @questrade 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/questrade-connects-b…] indexed:0 read:3min 2026-07-30 ·