binanceThe world’s largest crypto exchange with more than 300 million registered users, on Thursday launched a platform that allows AI agents to analyze markets and execute trades on behalf of users, bringing autonomous AI directly into the business of managing real money.
Called Agent OSThe platform allows developers to connect applications and AI agents to Binance’s financial infrastructure. It offers the exchange’s existing tools and services such as Binance APIs, Binance Wallet Agentic Hub, Binance x402 transaction verification and payment facilitation API, and Binance Skill Hub, along with newly introduced support for its Model Context Protocol (MCP). The platform also works with tools including ChatGPT and Codex from OpenAI, Claude Code and Cursor from Anthropic, allowing users to authorize brokers to access market data, view account information and execute trades.
However, as the AI race moves away from chatbots answering questions to agents capable of taking action, Binance is placing much of the responsibility for keeping them in check on users, who ultimately have to decide which agents they can access and trade and set limits on what they can do.
“Instead of complete freedom, we put the power in the hands of users to give them granular access control of what they can do through the agent,” said Jeff Li, vice president of product at Binance, in an interview. “We put [the control] at the account level to protect user funds.”
Binance does this primarily through dedicated “sub-accounts,” which users can assign to brokers and configure for specific activities, such as spot or futures trading. Withdrawals from those subaccounts are blocked by default, Li told TechCrunch, creating a sandbox around an agent’s activity.
Users can also choose whether an AI agent should seek approval for each order or can execute trades autonomously once its permissions are set, a Binance representative said. Binance does not impose a separate limit on how much an AI agent can trade or lose, so the amount a user transfers to the subaccount effectively serves as a limit.
When asked if Binance can see what leads an agent to make a particular trade, Li said the reasoning happens outside of its systems, either on the user’s computer or within the chosen AI application. “We can’t really see the reasoning for what the user’s action is,” he said.
That means Binance can monitor a broker’s resulting trading activity, but has limited visibility into whether a decision was influenced by faulty information or manipulation.
Li again pointed to the subaccount as the main line of defense when asked what would happen if an agent was manipulated via a fast injection attack or otherwise compromised. Binance also said that its existing security, risk control, and anti-money laundering policies for sub-account APIs apply to Agent OS at launch.
Trading is one of the first use cases that Binance is targeting. However, Li said agents could monitor markets, conduct research and risk analysis, react to signals and place orders autonomously or execute strategies such as arbitrage.
Agent OS is also designed to connect agents with on-chain payments and activities. Through Binance’s x402 integration, agents can send and settle payments, while its Agentic Wallet allows them to interact with decentralized finance tokens and protocols.
Unlike exchange trading, where Binance does not impose a separate limit on how much an agent can trade or lose within their sub-account, Agentic Wallet transactions have daily limits set by Binance. Regular swaps are capped at $50,000 per day, DeFi transactions have a default daily limit of $100,000, and x402 payments are capped at $20 per day, according to the company.
Li said Agent OS was Binance’s “first step” in providing developers with a platform to create AI-powered applications that can perform in the crypto and traditional markets.
Binance is not the only one opening its infrastructure to AI agents. Rival crypto exchanges have moved in the same direction, using MCP and other development tools to give AI applications direct access to market data and trading systems.
In March, Kraken launched an open source command line tool with an integrated MCP server that allows AI agents to execute actions including spot and futures trading. Coinbase followed in June with Coinbase for agentswhich connects AI agents directly to users’ accounts and allows them to trade, make payments, and execute other financial workflows within the limits set by users. Similarly, OKX Trade enabled agent on its platform by bringing an open source MCP toolset earlier this year.
When you purchase through links in our articles, we may earn a small commission. This does not affect our editorial independence.