The fintech community was stirred by the news that an analyst under the pseudonym CyrilXBT demonstrated the ability to connect Claude Code to live market data. This involves access to quotes for more than 17,000 stocks and cryptocurrencies, as well as fundamental metrics such as earnings reports, balance sheets, and cash flow statements. This is not just another experiment — it is a direct challenge to the established monopoly of the Bloomberg Terminal.

Three steps to professional analysis

The integration scheme described by the analyst is frighteningly simple and elegant. Just three steps — and the AI assistant gains access to professional financial analytics that previously took hours of manual searching and thousands of dollars in subscriptions.

The first step is running a command inside Claude Code to add the external service financial-datasets via HTTP transport. Essentially, this is registering an MCP server. The second step is authorization via OAuth in the browser, which takes no more than a minute. The third is interacting with the data in natural language. For example, you can ask about Apple's current price-to-earnings ratio, request Tesla's quarterly reports for the last four periods, or the price dynamics of bitcoin over a year.

Why this changes the game

The key point here is cost. An annual subscription to the Bloomberg Terminal costs analysts approximately $24,000. The emergence of a setup like this, which delivers comparable functionality in 60 seconds, will inevitably hit the wallets of those accustomed to paying for information. However, I also see a deeper trend here: we are witnessing the democratization of professional analytics, where AI becomes not just a tool but a full-fledged analytical partner.

Scaling agents and new risks

Special attention should also be paid to the workflow of Boris Cherny, one of the creators of Claude Code, described by CyrilXBT. He uses a smartphone as the primary interface and maintains between five and ten active sessions simultaneously. Each of these can spawn hundreds, and sometimes thousands, of auxiliary agents overnight to solve large-scale tasks. This is no longer just automation — it is the creation of an entire ecosystem of parallel computing.

However, such power requires strict discipline. The analyst highlights four critical elements for safe operation: a full-fledged interface for sending instructions from a smartphone, isolated parallel execution of tasks, verification of results without human involvement, and strict limits on time, budget, and volume. It is these frameworks that turn an overnight agent launch from a risky gamble into a manageable task.

My view: integrating AI with live financial data is an inevitable stage in the evolution of the market. Those who master these tools first will gain a colossal competitive advantage. The only question is how quickly traditional financial institutions will realize that their exclusive access to data is no longer a barrier to entry.