The world of professional financial analysis stands on the brink of a quiet revolution. I have learned that Anthropic's AI tool Claude Code has gained the ability to connect directly to live market data, covering more than 17,000 stocks and cryptocurrencies. This is not just another update—it is a direct challenge to the entrenched monopoly of expensive terminals like Bloomberg.
This is not about a theoretical possibility, but a practical solution that has already been tested and described by an analyst under the pseudonym CyrilXBT. The essence is to connect an external financial data service directly to Claude Code via the open MCP protocol. The entire setup takes about 60 seconds and consists of three simple steps: adding a server, authorizing via OAuth, and sending requests in natural language.
What this means in practice
Instead of spending hours searching for information across scattered sources or paying for complex APIs, an analyst can now simply ask Claude Code about Apple's current price-to-earnings ratio, Tesla's quarterly reports for the last four periods, or Bitcoin's performance over the past year. The AI itself accesses the data, processes it, and delivers a ready-made answer.
This is a particularly painful blow to Bloomberg's position. The terminal, for which analysts pay about $24,000 per year, suddenly looks like an anachronism. Why overpay for data access when the same information can be obtained through an AI assistant that also knows how to interpret it?
Scaling: thousands of agents overnight
But the most interesting part begins when we talk about scaling. CyrilXBT also drew attention to the workflow of Boris Cherny, one of the creators of Claude Code. He uses a smartphone as the primary interface instead of a laptop and maintains between five and ten active sessions simultaneously. Each of these can spawn hundreds or even thousands of auxiliary agents working in parallel.
In my assessment, this opens entirely new horizons for automation. At night, while the trader sleeps, their digital agents can analyze markets, test hypotheses, and prepare reports by morning. However, there are also serious risks here. Without strict limits on time, costs, and volumes, as well as without automatic verification of results, such a system could easily spiral out of control.
My expert opinion: we are witnessing the beginning of the end of an era when access to quality financial data was a privilege of the few. AI tools like Claude Code are democratizing analytics, but only for those willing to master new methods of work. Investors and analysts who adapt quickly will gain a colossal competitive advantage. The rest will have to catch up.