Trade a small Robinhood account by tracking politician trades
June 11, 2026 · Updated October 30, 2026 · AI Tutorials, Claude Code. Task: June 11, 2026 · Updated October 30, 2026 · AI Tutorials, Claude Code You can now build an AI trading agent on Robinhood that analyzes the market and places real trades for you through Claude Code. How an AI Trading Agent on Robinhood Works Robinhood just launched Agentic Trading, a beta feature that lets you connect an AI agent to a dedicated brokerage account and let it trade. It works through the Model Context Protocol, an open standard that connects AI agents to outside apps. You point Claude at Robinhood’s MCP endpoint, authenticate, and the agent can read your portfolio and place orders. Robinhood supports Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, and Grok today. I am not a trader. All my real investing runs on autopilot through Vanguard. But this Robinhood AI trading feature was too interesting to skip, so I funded a small test account and wired it up myself. If you want to go deeper on connecting tools like this, my Claude Code Skills Stack includes the workflows I use every week. One thing to know up front. The agentic account is a separate account, not your normal investing balance. I funded mine with $100 I could afford to lose, which is exactly how you should treat any beta trading tool. Get My Free AI Marketing Guide Run your marketing on AI systems, not more headcount Inside: 15 free Claude Code skills you install with one click, the AI tools I use and free automation templates. No coding needed to start. Join over 10,000 subscribers getting my weekly AI marketing newsletter. Unsubscribe anytime. Privacy policy. Connect Robinhood to Claude With MCP Setting up Robinhood agentic trading starts with one link and one prompt. Robinhood gives you an MCP connection URL inside the Agentic tab. The endpoint is https://agent.robinhood.com/mcp/trading. To add it in Claude Code, you run a short command in your terminal: Robinhood's own setup steps then have you type /mcp in Claude Code, select robinhood-trading, and authenticate. Its support article also lists setup steps for Claude Desktop and other AI platforms. I went a step further. My prompt told Claude to connect the Robinhood Trading MCP, read Robinhood’s Agentic Trading overview for context, and hold off on any trades until I confirmed the connection worked. Pasting the support article into Claude almost always makes the integration smoother. Adding the MCP is the easy part. Authentication is where most people get stuck. After the server connects, Claude told me two things were still needed: reload Claude Code, then finish the OAuth flow on desktop. You can only authenticate the agent on a desktop device, not your phone. The flow bounces between Claude and your browser a few times. You open an agentic account, agree to the terms, transfer funds in, verify on the Robinhood mobile app, then paste a localhost URL back into Claude. One step warns that the localhost page may show a “can’t connect” error. That is expected. You just copy the full URL from the address bar and hand it back to the agent. If you want a deeper primer on connecting services this way, my guide on Claude Code MCPs walks through the pattern I use for every integration. Set Up the Trading Strategy and Skill Connecting the agent is not a strategy. You still have to tell it what to trade and when to stay out. I built a Claude Code skill to handle that part. It took me 15 to 30 minutes and it monitors one signal in particular: the trading activity of politicians, CEOs, and executives. These people often hold information the rest of us do not, so the agent watches their public moves and weighs them when picking stocks. You do not have to copy my approach. You can ask Claude to analyze any strategy file and rebuild it around your own style, your own risk tolerance, and your own sectors. During setup, Claude asked me a long list of preferences. When to trade, when to avoid trading, how much cash to deploy, whether to use fractional shares. I am new to all of it, so every question was a small education. Then it did something I never asked for. Claude created a trade log in a markdown file and started recording every decision on its own. According to Robinhood’s agentic trading page, agents can analyze markets, build positions, and rebalance, but the logging was pure Claude initiative. That log matters more than it looks. Every buy and sell feeds back into the agent, so it keeps a record it can learn from over time. Let the AI Agent Trade and Review the Results; tools: Claude Code. Human role: The original post does not say how a person stayed involved.; limitations: This is a beta feature with known risks including bugs, errors, and hallucinations. The author advises assuming the agent is more likely to lose money than make it. Authentication requires a desktop device and mobile verification. The system is not 24/7; it stops when the local Claude Code instance closes. Source reliability is secondary, based on a personal blog post..
Tools
Published on Agent Work Atlas:
Overview
June 11, 2026 · Updated October 30, 2026 · AI Tutorials, Claude Code
Workflow
June 11, 2026 · Updated October 30, 2026 · AI Tutorials, Claude Code You can now build an AI trading agent on Robinhood that analyzes the market and places real trades for you through Claude Code. How an AI Trading Agent on Robinhood Works Robinhood just launched Agentic Trading, a beta feature that lets you connect an AI agent to a dedicated brokerage account and let it trade. It works through the Model Context Protocol, an open standard that connects AI agents to outside apps. You point Claude at Robinhood’s MCP endpoint, authenticate, and the agent can read your portfolio and place orders. Robinhood supports Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, and Grok today. I am not a trader. All my real investing runs on autopilot through Vanguard. But this Robinhood AI trading feature was too interesting to skip, so I funded a small test account and wired it up myself. If you want to go deeper on connecting tools like this, my Claude Code Skills Stack includes the workflows I use every week. One thing to know up front. The agentic account is a separate account, not your normal investing balance. I funded mine with $100 I could afford to lose, which is exactly how you should treat any beta trading tool. Get My Free AI Marketing Guide Run your marketing on AI systems, not more headcount Inside: 15 free Claude Code skills you install with one click, the AI tools I use and free automation templates. No coding needed to start. Join over 10,000 subscribers getting my weekly AI marketing newsletter. Unsubscribe anytime. Privacy policy. Connect Robinhood to Claude With MCP Setting up Robinhood agentic trading starts with one link and one prompt. Robinhood gives you an MCP connection URL inside the Agentic tab. The endpoint is https://agent.robinhood.com/mcp/trading. To add it in Claude Code, you run a short command in your terminal: Robinhood's own setup steps then have you type /mcp in Claude Code, select robinhood-trading, and authenticate. Its support article also lists setup steps for Claude Desktop and other AI platforms. I went a step further. My prompt told Claude to connect the Robinhood Trading MCP, read Robinhood’s Agentic Trading overview for context, and hold off on any trades until I confirmed the connection worked. Pasting the support article into Claude almost always makes the integration smoother. Adding the MCP is the easy part. Authentication is where most people get stuck. After the server connects, Claude told me two things were still needed: reload Claude Code, then finish the OAuth flow on desktop. You can only authenticate the agent on a desktop device, not your phone. The flow bounces between Claude and your browser a few times. You open an agentic account, agree to the terms, transfer funds in, verify on the Robinhood mobile app, then paste a localhost URL back into Claude. One step warns that the localhost page may show a “can’t connect” error. That is expected. You just copy the full URL from the address bar and hand it back to the agent. If you want a deeper primer on connecting services this way, my guide on Claude Code MCPs walks through the pattern I use for every integration. Set Up the Trading Strategy and Skill Connecting the agent is not a strategy. You still have to tell it what to trade and when to stay out. I built a Claude Code skill to handle that part. It took me 15 to 30 minutes and it monitors one signal in particular: the trading activity of politicians, CEOs, and executives. These people often hold information the rest of us do not, so the agent watches their public moves and weighs them when picking stocks. You do not have to copy my approach. You can ask Claude to analyze any strategy file and rebuild it around your own style, your own risk tolerance, and your own sectors. During setup, Claude asked me a long list of preferences. When to trade, when to avoid trading, how much cash to deploy, whether to use fractional shares. I am new to all of it, so every question was a small education. Then it did something I never asked for. Claude created a trade log in a markdown file and started recording every decision on its own. According to Robinhood’s agentic trading page, agents can analyze markets, build positions, and rebalance, but the logging was pure Claude initiative. That log matters more than it looks. Every buy and sell feeds back into the agent, so it keeps a record it can learn from over time. Let the AI Agent Trade and Review the Results
Reported result
The agent executed four initial trades (insurance stocks and Norwegian Cruise Line) after funds settled. The author reported a negligible gain of approximately $0.33 at market open, explicitly stating this provides no meaningful data on returns. The workflow is not fully autonomous; it requires Claude Code to remain open on the desktop, functioning only while the user is active at their desk.
Human role
The original post does not say how a person stayed involved.
Limitations
This is a beta feature with known risks including bugs, errors, and hallucinations. The author advises assuming the agent is more likely to lose money than make it. Authentication requires a desktop device and mobile verification. The system is not 24/7; it stops when the local Claude Code instance closes. Source reliability is secondary, based on a personal blog post.
Try it
I want to set up a low-risk AI trading experiment using Claude Code and Robinhood's Agentic Trading beta. First, create a new, separate Robinhood Agentic account and fund it with [replaceable input: e.g., $100] that I can afford to lose. Install Claude Code and add the Robinhood MCP endpoint using the command: `claude mcp add robinhood-trading --transport http https://agent.robinhood.com/mcp/trading`. Complete the OAuth flow on my desktop and verify via the mobile app. Next, guide me through creating a Claude Code skill that monitors [replaceable input: e.g., politician trading disclosures] to suggest stocks. Define my risk parameters: [replaceable input: e.g., max position size, sectors to avoid]. Before enabling any real trades, run a dry-run simulation where the agent analyzes the market and proposes a trade log without executing orders. Show me the proposed trades and reasoning. Only after I explicitly confirm the logic and accept the risks should you enable the agent to place real orders. Ensure Claude Code remains open during trading hours. If authentication fails or the MCP connection drops, stop immediately and report the error. Do not proceed if I have not confirmed the dry-run output.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.