Claude Code now sees the market: the AI agent has gained access to data on 17,000+ stocks and cryptocurrencies.
The financial data market is undergoing a quiet revolution. An analyst under the pseudonym CyrilXBT has demonstrated how to connect Claude Code to live market data—from quotes for more than 17,000 stocks and cryptocurrencies to earnings reports, balance sheets, and cash flow statements. All of this is done with a single command and takes about a minute. In essence, this is a direct blow to the monopoly of the Bloomberg Terminal, which costs professionals a hefty sum.
How it works: three steps to financial omniscience
The mechanics are simple and elegant. The connection is made through the open MCP (Model Context Protocol), which allows AI assistants to access external services. The first step—inside Claude Code, a command is executed to add the financial-datasets service via HTTP transport. The second—authorization via OAuth in the browser. The third—queries in natural language. Want to know Apple's current price-to-earnings ratio or market capitalization? Just ask. Need Tesla's quarterly reports for four periods or Bitcoin's dynamics over a year? No problem.
Previously, this required either a Bloomberg Terminal costing $24,000 a year, complex APIs, or hours of manual searching across disparate sources. Now, the AI agent becomes a full-fledged analytical tool that not only finds data but can also interpret it in the context of reasoning.
Who benefits and what's next?
A sustainable advantage will go to those who first master the combination of "AI reasoning + live data." Quants, analysts, and portfolio managers are the main beneficiaries of this technology. The advantage compounds daily, like a research edge. Every day of use makes the analyst stronger and their conclusions more accurate.
It is especially telling that Boris Cherny himself, one of the creators of Claude Code, already uses a smartphone as the primary interface for managing processes. He maintains between five and ten active sessions simultaneously, each capable of spawning hundreds or even thousands of auxiliary agents overnight. But such power requires discipline: strict limits on time, costs, and volume, as well as automated verification of results without human involvement—otherwise, chaos is inevitable.
My verdict: this is not just a convenient integration but a paradigm shift. When AI gains access to real market data in real time, its role shifts from "text generator" to "analytical engine." The only question is how quickly traditional financial institutions realize that their exclusive access to data is no longer a barrier to entry. Those who ignore this trend risk being left behind.