The crypto trading market is entering a new phase of automation. Now, creating complex trading indicators on the TradingView platform no longer requires knowledge of Pine Script or deep programming skills. The combination of TradingView MCP and the Claude Fable 5 model allows any trader to build an effective tool in minutes.
As the lead analyst at Cryptalist, I have carefully studied this approach. The method, proposed by experienced analyst Miles Deutscher, demonstrates that even someone far removed from the technical side of the process can create full-fledged market indicators. This is not just news—it is a paradigm shift in trader education.
What is needed for setup?
To start the process, three key tools are required: Claude Code, the TradingView desktop application, and a Node.js environment version 18 or higher. The first step is to install TradingView MCP itself. To do this, open Claude Code and give the command to install the MCP server, specifying the repository link.
The second stage is the most important: describing the future indicator in plain language. There is no need to think about code. It is enough to explain the logic as if you were telling it to another trader: under what conditions a buy signal should be generated, what data to analyze. Create a separate folder, open it in Claude Code, and in the prompt specify that the indicator is written for TradingView in Pine Script V6.
Notably, the model can even conduct preliminary research for the user if you are unsure where to start. This radically simplifies the entry for beginners.
How to run the indicator
The third step is transferring the generated code to TradingView. Copy the Pine Script code created by the model. Then, in TradingView, open the "My Scripts" section, create a new script, and paste the code starting from the first line. The indicator is immediately added to the chart and begins to work.
Deutscher also shares practical tips. It is better to first check signals on higher timeframes—they are cleaner and more informative. It is recommended to set up alerts and turn the indicator into a strategy for backtesting on historical data. When errors appear, it is best to debug the code using the Opus model in high-effort mode.
Overall, this scheme is a true game-changer. You can build your first working indicator today, without a single day of programming experience.
Cryptalist Expert Opinion: This approach radically democratizes access to technical analysis. However, I would caution against blindly trusting generated indicators. Always conduct backtesting and visual analysis on historical data. AI is a powerful assistant, but the final decision to enter a trade should always remain yours. The market does not forgive automated mistakes.