Claude Code has gained direct access to data on 17,000 stocks and cryptocurrencies: a replacement for Bloomberg?
A quiet revolution is brewing in the world of financial analytics. I have carefully studied a new integration that allows the AI assistant Claude Code to connect to live market data for over 17,000 stocks and cryptocurrencies. This is not just a technical trick, but a potential game-changer for quants, analysts, and portfolio managers.
The essence is that an external financial data service is connected to Claude Code via the MCP (Model Context Protocol). The entire setup process takes about a minute and consists of three simple steps. First, a command is executed to add the financial-datasets service via HTTP transport. Then, authorization is done through OAuth in the browser. And finally, data is worked with in natural language. For example, you can ask about Apple's current price-to-earnings ratio, Tesla's quarterly reports for the last four periods, or Bitcoin's price dynamics over a year.
A direct replacement for the Bloomberg terminal?
Previously, accessing such data required a Bloomberg terminal, complex APIs, or hours of manual searching. Now, an analyst under the pseudonym CyrilXBT has shown how a single command opens access to data on earnings, balance sheets, cash flow, and quotes. The cost of the alternative is obvious: a Bloomberg terminal costs about $24,000 per year. The emergence of such a combination is unlikely to please specialists accustomed to expensive tools.
Who benefits from this?
A sustainable advantage will go to those who learn to combine Claude Code's reasoning with access to live data. This is a research edge that accumulates with each day of use. The value here is not in the individual steps, but in their combination: a common tool + a stream of up-to-date market data in one interface. This is an open standard where Claude Code acts as the shell, and the data is provided by a third-party service.
In parallel, it is worth noting a broader trend: Claude Code co-founder Boris Cherny uses a smartphone as his primary interface, running 5-10 active sessions in parallel. Each of them can spawn hundreds or even thousands of auxiliary agents overnight. For such a scheme, four elements are critical: a full task management interface, isolated parallel execution, automatic verification of results, and strict spending limits. Without them, overnight agent work turns into chaos.
My view: This integration is not just a convenience, but a signal of the democratization of market access. If expensive terminals were once a barrier to entry, now any retail investor with a subscription to an AI tool gets analytical power at the level of institutional players. The only question is how quickly traditional financial giants will adapt to this new world, where the speed of analysis matters more than the volume of data.