AI agents, Claude and ChatGPT

Can Claude trade stocks for you? What it can and can’t do

Claude can read a chart, research a company and write a trading script. Placing a real order is a different job: it needs a broker connector, your permission and a session that is still running. Here is what works in November 2026, what Anthropic allows, and how to keep the risk small.

[

Updated November 16, 2026

]
•
[

15

 

min to read

]

The short answer

Not by itself. In a chat, Claude can read a chart screenshot, research a stock and run code, but it has no brokerage account. It places an order only through a broker connector you add, such as Robinhood’s or Alpaca’s MCP server, and only while a session runs. Anthropic’s own browser and Duet agents won’t trade securities at all.

What can Claude do for a trader on its own?

A lot, as long as the job is reading, reasoning or writing. In a normal chat, with nothing connected, Claude can:

  • Read a chart screenshot. Claude understands images, so you can paste a chart and ask about the trend, the levels or a pattern. Anthropic’s vision docs say it “might hallucinate or make mistakes when interpreting low-quality, rotated, or very small images,” and ask you to verify its readings “especially for high-stakes use cases.” Check every price it reads off the axis. Our guide to AI chart analysis tests that limit on a real candlestick chart.
  • Research with web search. With web search turned on, Claude looks things up and every answer includes citations, so you can open what it read. Without it, Claude answers from training data that stops at a cutoff: June 2026 for the current models.
  • Write and run code. On every plan, Claude can run code in an isolated sandbox inside the chat. Upload a file of daily prices and it can compute an RSI, draw the chart or test a simple rule on that data. Our guide on how to backtest a trading strategy covers the traps.
  • Explain and plan. It can explain how an option’s payoff works, turn your trading rules into a checklist, or argue the other side of an idea before you act on it.
Check a chart before you trade

This is a screenshot of [TICKER] on the [TIMEFRAME] chart. Describe the trend, the two nearest support and resistance levels, and what the RSI shows if it is on the chart. Then list what would prove this read wrong. Mark which numbers you read off the image and how sure you are of each one. Don’t tell me whether to buy or sell.

For more like it, see our trading prompts for charts, research and risk.

Claude is a strong general analyst: it can work through a long filing, write working code and lay out both sides of an argument. If you are choosing an assistant for this kind of work, we compare the two best-known ones task by task in Claude vs ChatGPT for trading, and answer the same question for ChatGPT in can ChatGPT trade for you? For Grok, see can Grok trade for you? Our wider LLM trading comparison sets all four, plus Gemini, side by side on the same tasks.

What can’t Claude do by itself?

Out of the box, Claude has no brokerage account, no live price feed and no view of your positions. Five limits follow from that:

What Claude can’t do on its own, and what changes it
TaskClaude on its ownWhat changes it
Place an orderNo. A chat has no route to a brokerA broker connector that offers an order tool
See live pricesOnly what its training data or a web page saysA connector to a broker’s or a data provider’s feed
Hold your account or keysNo. It has no login or wallet of its ownA connector you sign in to, or API keys in a config file
Watch a market with the chat closedNoA Claude Code scheduled task, at most once an hour
Keep a stop in placeNo. A stop that only exists in a chat is gone when the chat endsA real stop order resting at your broker

Anthropic draws the same line in its own agent products. Claude in Chrome, the extension that clicks through websites for you, lists “Executing financial trades or investment transactions” among the actions it is prohibited from taking, whatever permissions you give it. Claude Duet, the agent app Anthropic opened as a research preview on October 21, 2026, keeps working when you step away. Yet Anthropic writes: “A few things are off-limits even with your approval, like trading securities or moving money between accounts.” So asking Claude to log in to your broker’s website and buy shares will not work.

What about watching a position? Claude Code, Anthropic’s coding agent, can run a saved prompt on a schedule in Anthropic’s cloud, even with your laptop closed. Its docs reject schedules that run more often than once an hour, and say the saved prompt “can’t act as approval or consent for actions during the run.” That is fine for a morning summary. It is no substitute for a stop.

How do people connect Claude to a brokerage account?

Through MCP, the Model Context Protocol: an open standard that lets an AI app use outside tools. A broker runs an MCP server, a service that offers tools such as “get positions” or “place order.” You add it to Claude, sign in, and Claude can call those tools when you ask. There are three common setups:

  1. A connector in the Claude apps. In Claude on the web or the desktop app, open Customize, then Connectors, choose “+ Add” and “Add custom connector,” and paste the server URL your broker gives you. Free plans can add one custom connector.
  2. Claude Code. The same server, added from the terminal with claude mcp add. Traders who code use it to combine broker tools with their own scripts.
  3. A local server. A program that runs on your own computer and is listed in Claude Desktop’s config file, often with your API keys written into it. An API key is a password a program uses to act on your account, so anyone who has it can trade with it.

When Claude wants to use a tool, it shows you an approval request. Anthropic’s connector guide says to “only click ‘Allow always’ when using a server and tool that you trust to run unsupervised.” For a tool that places orders, the safe answer is not to.

Three MCP servers traders connect to Claude
ConnectorMade byWhat it can doWorth knowing
Robinhood Trading MCPRobinhoodReads your accounts; equities, options and crypto toolsTrades only in a separate agentic account you fund
Alpaca MCP serverAlpaca, open sourceMarket data and orders for stocks, options and cryptoStarts in paper trading; live trading takes a setting change
TradingView MCP serverTradingViewQuotes, screeners, technical ratings, news and alertsPlaces no orders

Paper trading means simulated orders with pretend money against real prices. Alpaca’s server starts there: its README sets ALPACA_PAPER_TRADE to true by default and tells you to set it to false for live trading. Its security notice is plain: “This server can place real trades and access your portfolio.” If you only want Claude to read market data from TradingView, see how to connect Claude to TradingView with MCP.

There is a fourth route, the one people mean by a “Claude trading bot”: asking Claude Code to write a bot that calls a broker’s API and runs on a server. Then your code trades, and Claude is only the programmer. The bot does exactly what the code says, bugs included, so run it on paper first. If someone offers to sell you a ready-made one, read is AI trading legit? before you pay. A “Claude trading skill” is something else again. Skills are folders of instructions, scripts and resources that Claude loads for a specialized task. A skill can teach Claude a method, but connecting it to a market is the job of an MCP connector. Our guide to building a Claude trading bot with Claude Code covers that route in full, brokers, keys and what goes wrong included.

Can Claude trade for you on Robinhood?

Yes, through Robinhood’s agentic trading, which Robinhood launched in May 2026 for customers who want to connect their own AI agents. The setup, from Robinhood’s support page:

  1. Add the server

    In Claude, add a custom connector with the URL https://agent.robinhood.com/mcp/trading. In Claude Code, run claude mcp add robinhood-trading --transport http https://agent.robinhood.com/mcp/trading, then type /mcp and pick robinhood-trading.

  2. Sign in and open the account

    Authenticate with Robinhood and you are prompted to open an MCP account, a separate account just for your agent. You need a primary individual investing account in good standing.

  3. Fund it with money you can afford to lose

    Robinhood says your agent “can only trade with funds you deposit into this account.” The deposit is your real limit.

  4. Decide on approvals

    Trade approvals are off by default for MCP accounts, so turn them on in the account’s Safety Controls if you want to place each order yourself. Robinhood warns that if you’ve asked it to act without your approval, “it can place trades without your confirmation.”

Two lines on Robinhood’s page are worth reading twice. First, the agent gets read access to “all your Robinhood accounts, including your Robinhood account numbers,” plus your positions, balances and order history, even though it “can only place trades in your Robinhood Agentic account.” Second, the responsibility stays with you: “You are ultimately responsible for the trades your AI agent places in your account,” and AI agents “can make errors, misinterpret instructions, act on incomplete or outdated information, and may behave in unexpected ways.”

Expect some friction too. Since late August 2026, some traders have reported that Claude declines to place orders through Robinhood’s connector while others say theirs still works, according to a detailed user report. We found no rule from Anthropic about trades through connectors, but its usage policy says its products include “real-time safeguards that may block or limit certain outputs.” If Claude reads your account but won’t place orders, first check that the agentic account is open and funded.

Robinhood is also building agents into its own app. On September 29, 2026 it announced Robinhood Agents, coming to eligible US customers: you pick a model from one of several AI labs inside the Robinhood app, so there is no connector to set up. We look at them, and at the alternatives, in Robinhood Agents and its alternatives.

What can go wrong if you let Claude place trades?

Five risks come up again and again. None is unique to Claude: any AI model wired to an account carries them.

Risks of letting Claude place trades, and how to limit them
RiskWhat it looks likeHow to limit it
Confident mistakesA wrong level read off a screenshot, a misread instruction, an order for the wrong sizeKeep approvals on and read every order before you allow it
Stale dataAn answer built on training data or a delayed quote instead of the live priceAsk where each number came from and when; check the price at the broker
Prompt injectionHidden text in a web page, a news story or a tool reply that tells Claude to do something you never askedKeep trading sessions away from untrusted pages; connect only servers you trust
Keys and permissionsAn API key saved in a config file, a connector that can read all your accountsUse paper or a small separate account; remove connectors you no longer use
No stop when the chat endsA plan to “sell if it drops 5%” that only exists in a conversationPlace the stop as a real order at the broker

Prompt injection deserves a closer look, because it turns reading into acting. It means instructions hidden in content the model processes. Anthropic’s own research on browser agents says “prompt injection is far from a solved problem, particularly as models take more real-world actions,” and that even “a 1% attack success rate” still “represents meaningful risk.” Its connector guide adds that malicious MCP servers “may include hidden instructions that try to make Claude perform unintended actions.” The session to keep separate is the one that can both read the web and place orders.

A safer way to try it

  1. Start on paper

    Run the whole flow with simulated money first, for example on Alpaca’s paper account, until you trust every step.

  2. Separate the money

    Trade from an account that holds only what you could lose, like Robinhood’s agentic account.

  3. Keep approvals on

    Never choose “Allow always” for an order tool. Read the symbol, side, size and order type before you allow it.

  4. Put protection at the broker

    Send stops and limits as real orders, so they stay in place when the chat closes.

  5. Give it only the tools it needs

    Turn off the tools a chat doesn’t need, and don’t mix trading with browsing.

  6. Write down your rules

    Start each session with your limits: the largest size you’ll trade, the markets you trade and when to stop for the day.

What do Anthropic’s rules say about trading and financial advice?

Anthropic’s Usage Policy, in the version effective November 12, 2026, treats finance as a high-risk area. It defines the case as “a personalized recommendation to buy, sell, hold, or allocate among specific investment products, such as securities, funds, digital assets, or annuities.” When Anthropic’s products are used to make that kind of recommendation, two controls apply:

  • A qualified person in the loop. “A qualified person must meaningfully review a High-risk AI Recommendation, with the authority to change or modify it,” before it is delivered as advice to someone who might rely on it, or used to carry out a decision.
  • Disclosure. The person who receives the advice “must be clearly told that AI was used to produce it.”

The policy also lists what falls outside those requirements. That includes general or educational content, such as explaining “how investing works” without applying it to your circumstances; “internal drafting, research, summarization, or analysis”; and “carrying out a decision a person has already made.” For agents, users are responsible for making sure the agents they build or deploy comply, “including actions those agents take through tools, browsers, or connected systems.”

Read it as a line between two kinds of use. Research, explanation and carrying out a decision you already made are listed outside the requirements. Personalized buy or sell calls delivered to people who rely on them need a qualified person reviewing them and a clear AI label. The policy adds that running into one of Anthropic’s real-time blocks “does not by itself indicate a violation.”

Where does an AI trading agent fit, and what does Ethy do?

Claude is a general assistant you can wire to a broker yourself. An AI trading agent is built for the job from the start: it comes with market data, an account to trade from and rules that keep working after you close the tab. Ethy is one: the AI trading agent you ask before you trade. There is no broker to connect and nothing to install.

  • It reads the chart on four timeframes at once. The daily, 4-hour, 1-hour and 15-minute charts, with the trend on each, support and resistance, RSI and MACD divergences, Fibonacci levels, VWAP, volume nodes, patterns and an overall bias.
  • It finds out why a market moved. A web search with citations, plus the price and how its peers moved.
  • It tests an idea on past data. Describe a rule in plain words and Ethy backtests it on up to a year of history, with every entry and exit marked.
  • It watches levels and indicators. Price alerts on a move or a level, and indicator alerts on an RSI level, a 9/21 EMA cross or a MACD cross, in the app or on Telegram.
  • It knows your trading plan. You write your rules once, in four parts: risk, markets, process and goals. Ethy reads them first in every chat and tells you when an idea goes against them. It never blocks you.

Ethy also does the trading side. From the chat it places orders on Hyperliquid perpetuals, or perps: contracts that track a price with no expiry date and can use leverage, which magnifies losses as well as gains. They cover crypto, plus stocks, indices, commodities and FX listed on trade.xyz, an exchange that runs on Hyperliquid, and Ethy also runs spot swaps. Whether a chat order shows you a confirmation card first is a setting you choose. Automations trade on their own once you activate them, and paper mode tests one with live prices and no money. Stop loss and take profit orders sit on Hyperliquid itself, so they fire even when Ethy is closed. Every account gets a wallet at sign-up: your balance lives in a wallet that belongs to you, and you can export its key at any time.

Claude remains the better tool for open-ended work beyond trading: long documents, software, anything that is not a market. Ethy is narrower, and it covers the trading jobs from the first question to the order.

Summary

  • Claude can’t trade by itself: it has no brokerage account, no live prices and no way to act while no session is running.
  • It places orders only through a broker’s MCP connector, such as Robinhood’s Trading MCP or Alpaca’s MCP server, and asks before it uses a tool.
  • Anthropic built Claude in Chrome and Claude Duet so they won’t trade securities, even with your approval.
  • The main risks are confident mistakes, stale data, prompt injection, exposed keys and stops that only exist in a chat.
  • Start on paper, fund a small separate account, keep approvals on and put your stops at the broker.
  • An AI trading agent such as Ethy comes with the market data, the account and rules that keep running after you close the tab.

Questions people ask

Can Claude trade crypto for you?

Only through a connector to an account that can trade crypto. Robinhood’s Trading MCP includes crypto tools for its agentic account, and Alpaca’s MCP server supports crypto orders, starting on paper. Claude itself holds no coins and no keys. Crypto trades around the clock, so a position can move while no chat is open: keep a real stop order at the exchange or broker.

Is Claude trading legit?

Claude is a real assistant from Anthropic, and broker connectors such as Robinhood’s are real products. But Anthropic built its own agents so they won’t trade securities, so anything sold as a “Claude trading bot” is made by someone else. Judge it like any third-party trading software, test it on paper and walk away from anyone who promises returns.

Can Claude trade options on Robinhood?

Robinhood’s Trading MCP lists options tools next to its equities and crypto tools, so a connected Claude can work with options inside your agentic account. Options can lose their whole value quickly. Keep trade approvals on and check the strike and the expiry before you allow an order.

Does Claude have to stay open for a trade to happen?

For Claude to place an order, a session must be running: a chat, a Claude Code session, or a scheduled task that runs at most once an hour. Orders already resting at your broker, such as a stop order, stay there whether Claude is open or not. That is why your protection belongs at the broker, not in the chat.

What are Claude trading skills?

A skill is a folder of instructions, scripts and resources that Claude loads for a specialized task, such as an earnings checklist or a script that computes an indicator. A skill doesn’t connect Claude to a market or a broker; MCP connectors do that. Read a skill’s scripts before you run it, as you would with any code.

Can Claude backtest a trading strategy?

Yes, in code. Upload price data and Claude can write and run a backtest in its sandbox, or build a fuller one in Claude Code. The result is only as good as the data and the code, so check how it handles slippage and look-ahead bias, which is using information a trader could not have had at the time.

Sources

  1. Anthropic: Usage Policy (effective November 12, 2026)anthropic.com
  2. Claude Help Center: Claude in Chrome permissions guidesupport.claude.com
  3. Claude: Introducing Claude Duet (October 21, 2026)claude.com
  4. Claude Code docs: Automate work with scheduled taskscode.claude.com
  5. Claude Help Center: Get started with custom connectors using remote MCPsupport.claude.com
  6. Claude Help Center: Enable and use web searchsupport.claude.com
  7. Claude Help Center: Create and edit files with Claudesupport.claude.com
  8. Claude Help Center: What are skills?support.claude.com
  9. Claude docs: Visionplatform.claude.com
  10. Claude docs: Models overviewplatform.claude.com
  11. Anthropic: Mitigating prompt injections in browser use (November 24, 2025)anthropic.com
  12. Robinhood: Onboarding an external agentrobinhood.com
  13. Robinhood: Trading with your agentrobinhood.com
  14. Robinhood Newsroom: HOOD Summit 2026 (September 29, 2026)robinhood.com
  15. Alpaca: alpaca-mcp-server, the official MCP server (GitHub)github.com
  16. TradingView: MCP Server documentation (beta)tradingview.com
  17. Saving to Invest: I let Claude trade my Robinhood account (user report, updated November 2, 2026)savingtoinvest.com

Trading involves risk, including the loss of your money. Ethy AI is a research and trading tool and does not give investment advice or recommendations. Backtests are simulations on historical data and do not predict future results.

Ethy blog

Read more

The $ETHY ecosystem

Stop watching charts.
Start living.

Deploy your AI trading agent in one click.