Binance launched a system on Thursday allowing AI agents to analyse markets and execute trades on behalf of users, moving autonomous software directly into the management of real money.
How the platform works
Called Agent OS, the platform connects AI applications to Binance’s financial infrastructure. It combines existing tools such as the Binance APIs, Binance Wallet Agentic Hub, Binance x402 transaction verification and payment facilitator API, and Binance Skill Hub with new support for the Model Context Protocol (MCP).
The system works with tools including OpenAI’s ChatGPT and Codex, Anthropic’s Claude Code, and Cursor. Users can authorise agents to access market data, view account information, and execute trades.
Who holds the keys
As the industry shifts from chatbots that answer questions to agents capable of taking action, Binance places much of the responsibility for oversight on users. They must decide what agents can access, what they can trade, and set limits on their activities.
“Instead of total freedom, we put the power in users’ hands to give them the granular access control of what they can do through the agent,” said Jeff Li, vice president of product at Binance. “We put [the control] at the account level to protect the users’ funds.”
Sub-accounts as a firewall
Binance primarily uses dedicated “sub-accounts” to manage this risk. Users assign these to agents and configure them for specific activities, such as spot or futures trading. Withdrawals from those sub-accounts are blocked by default, creating a sandbox around an agent’s activity.
Users can choose whether an AI agent must seek approval for every order or can execute trades autonomously once its permissions are configured. Binance does not impose a separate cap on how much an AI agent can trade or lose. The amount a user transfers into the sub-account effectively serves as the limit.
Blind spots in decision making
Li said the reasoning behind a particular trade happens outside Binance’s systems, either on the user’s computer or within their chosen AI application. “We really cannot see the reasoning of what the user’s action is,” he said.
That means Binance can monitor an agent’s resulting trading activity but has limited visibility into whether a decision was influenced by faulty information or manipulation.
Security and limits
Li again pointed to the sub-account as the main line of defense when asked what would happen if an agent were manipulated through a prompt-injection attack or otherwise compromised. Binance also said its existing security, risk-control, and anti-money-laundering policies for subaccount APIs apply to Agent OS at launch.
Trading is one of the first use cases Binance is targeting. Li said agents could monitor markets, conduct research and risk analysis, react to signals, and autonomously place orders or execute strategies such as arbitrage.
Agent OS is also designed to connect agents to payments and on-chain activity. Through Binance’s x402 integration, agents can send and settle payments, while its Agentic Wallet allows them to interact with tokens and decentralized-finance protocols.
Unlike exchange trading, where Binance does not impose a separate cap on how much an agent can trade or lose within its subaccount, Agentic Wallet transactions carry Binance-set daily limits. Regular swaps are capped at $50,000 a day, DeFi transactions have a default $100,000 daily limit, and x402 payments are limited to $20 a day, according to the company.
The wider market
Li said Agent OS was Binance’s “first step” toward giving developers a platform to build AI-powered applications that can act across crypto and traditional markets.
Binance is not alone in opening its infrastructure to AI agents. Rival crypto exchanges have been moving in the same direction, using MCP and other developer tools to give AI applications direct access to market data and trading systems.
In March, Kraken launched an open-source command-line tool with a built-in MCP server that allows AI agents to execute actions including spot and futures trades. Coinbase followed in June with Coinbase for Agents, which connects AI agents directly to users’ accounts and allows them to trade, make payments and execute other financial workflows within user-set limits. Similarly, OKX enabled agentic trading on its platform by bringing an open-source MCP toolkit earlier this year.
