Creating your own trading indicators for TradingView no longer requires programming skills. Thanks to the combination of TradingView MCP and the Claude Fable 5 language model, even those far from the technical side can assemble effective market tools.
One well-known analyst shared a workflow that, in his opinion, every trader should master. He himself, without being a programmer, was able to create working indicators simply by describing his idea in natural language. This, in my view, marks the beginning of a new era in trading, where the barrier to entry for creating custom strategies is virtually disappearing.
What is needed for setup
To launch the process, three components are needed: 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, a command is given in Claude Code to install the MCP server, specifying the link to the corresponding repository.
The second step is the most important. You need to describe the future indicator in simple language. The analyst advises explaining the strategy as if you were telling it to another trader: think not about code, but about trade conditions. For this, a separate folder is created, opened in Claude Code, and the request explicitly states that the indicator is written for TradingView in Pine Script V6, and the conditions for a buy signal are described in detail.
Notably, the model is even capable of conducting research on behalf of the user, which significantly simplifies the work for those who do not know where to start.
How to run the indicator
The third step is transferring the generated code to TradingView. The Pine Script code is copied, then in TradingView the "My Scripts" section is opened, a new script is created, and the code is pasted from the first line. After that, the indicator is added to the chart and starts working immediately.
The analyst also gives several practical tips. Signals are best checked first on higher timeframes, as they are cleaner than on lower ones. Additionally, he recommends setting up alerts and turning the indicator into a strategy for backtesting on historical data. When errors occur, the code should be debugged using the Opus model in high-effort mode.
Expert opinion: This method is not just a convenient life hack, but a true paradigm shift. It democratizes access to complex analysis tools, allowing traders to focus on the logic of the strategy rather than the syntax of the language. However, it is worth remembering that automatic code generation is only the first step; backtesting and visual verification of the indicator on historical data remain critically important to ensure its effectiveness and the absence of overfitting errors.