Have you ever wished you could ask an AI Assistant to analyze your portfolio and tell you how your stocks are doing today? With the latest release of Kite MCP (Model Context Protocol) from Zerodha, that future is here. The MCP lets you connect your Zerodha account with Claude and ask it to work for you. This connection allows investors to chat with their portfolio and ask complex market questions, all in simple English. Whether you are a seasoned trader or a complete beginner, this integration will completely change your investing workflow. In this guide, we will deep dive into the integration of Zerodha Kite MCP server with Claude and learn how to transform our investment workflow using it.
Kite MCP acts as a connector between your LLM (Large Language Model) and the external tools available, in a structured way. It is like a standardized way for LLMs to talk to or work with external systems, making it easier to perform multi-step tasks. The MCP also acts like a contextual data layer that allows AI to see the live data.
The traditional Kite API gives us structured data based on manual queries. We would then have to analyze the results and get the insights ourselves. Now with Kite MCP, we can instantly ask portfolio queries through natural language prompts like “What’s my P&L today?”. Claude can give you personalized responses to such queries based on your use case and context.
This is possible as the Kite MCP allows Claude to access all the portfolio-related tools and use them when required. So, now, Claude can analyse our holdings, our previous orders, our P&L, and much more. Together, Zerodha’s Kite MCP and Claude, give us a powerful AI investing assistant built directly into our workflow with a single line of code.
Here’s how you can integrate Kite MCP with Claude and use it as your personal stock trading assistant.
First, you need to download the Node from the official website https://nodejs.org/en/download based on the operating system you are using.
Once downloaded, verify its installation using the following command:
# Verify npm version:
npm -v # Should print the downloaded version
The next step is to set up the configuration file for Claude. Note that the configuration file is unique for each client.
Since we are using Claude’s desktop app, we will need to edit Claude’s configuration file. To do this:
{
"mcpServers": {
"kite": {
"command": "npx",
"args": ["mcp-remote", "https://mcp.kite.trade/sse"]
}
}
}
Now that we have successfully added the Zerodha Kite MCP server to Caude, it’s time to test it out.
Prompt: “Give me data for nifty 50 for last 20 days with kite”
Output:
When we put in the query, Claude successfully detects the Kite MCP AI tools and starts to list which tools it would use. It then asks us to log in to Kite with the link. Once we click on the link and fill in our account details, we will be logged in. Then return to Claude and type “Done” and it will answer your query utilizing the provided tools.
Prompt: “What is my profit in Kite for the day?”
Output:
Again, it will ask you to log in; follow the previous steps to do so. Type “Done” and it will answer you using Zerodha AI.
Also Read: 7 Best AI Stock Market Software for Trading in 2025
We have tested our personalized trading assistant in Claude using the Kite MCP, and the outputs are looking good. However, since the Zerodha AI MCP can access all the information from the portfolio, it may raise some concerns regarding data security.
Zerodha considered security and privacy as important aspects while building the Kite MCP. Here are some points that Zerodha makes sure:
Although Kite MCP is looking promising, there are some points that we should consider as small limitations of Zerodha’s AI.
The launch of Kite MCP has taken AI-assisted trading and investing to the next level. Kite MCP’s integration with Claude and other MCP clients makes it easily accessible to everyone. Through this integration, we get access to a personalized AI assistant, that can retrieve info, analyze it, and draw insights from your Zerodha account using natural language prompts. This automated trading and investing process can change the world of the stock market forever. As we explore the capabilities of this integration and use it to enhance our trading and investment strategies, stay updated with the future developments of Zerodha AI as it continues to evolve.
A. Zerodha MCP (Model Context Protocol) enables AI assistants like Claude to directly interact with your Zerodha account using natural language prompts. Unlike the traditional Kite API which requires manual querying and interpretation, MCP lets Claude fetch, analyze, and respond to data-driven questions in real-time.
A. Yes, it’s safe. Claude does not store your Zerodha credentials. Authentication is handled securely through Zerodha’s own login flow every time you use MCP tools, ensuring that your account remains protected.
A. No. The setup is simple and requires only basic steps like installing Node.js and editing a configuration file. You don’t need to write or understand complex code to complete the integration.
A. This is a current limitation of the integration, likely implemented for enhanced security. Each session requires re-authentication to prevent unauthorized access to your Zerodha account.
A. Claude can analyze your portfolio, fetch P&L data, provide stock performance insights, and even compare stocks or market indices – all through simple English prompts, thanks to the Kite MCP tools.