About Zerodha Trade GPT
Zerodha Trade GPT is a TypeScript-based MCP server for real-time stock trading, connecting LLMs to the Zerodha Kite Connect API. It exposes tools that can place live buy and sell orders.
Key features
- 01Execute live buy and sell orders
- 02Accept natural-language trade requests
- 03Provide structured trading tools
- 04Use the TypeScript SDK
- 05Communicate over Stdio
Use cases
- 01Place a stock buy order through natural language
- 02Place a stock sell order through natural language
MCP support
It exposes `buy-stock` and `sell-stock` tools to MCP clients and uses StdioServerTransport for communication with the backend.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEZerodha Trade GPT
Zerodha Trade GPT is a real-time stock trading agent that connects LLMs (Claude.ai) with Zerodha's Kite Connect API using the Model Context Protocol (MCP) and a TypeScript-based backend.
Through natural language commands like "Buy 5 shares of INFY", LLMs can place actual stock trades via secure, live MCP tools (buy-stock and sell-stock).
Features
- Real-time buy/sell order execution
- LLM-driven input (Claude, ChatGPT, or any MCP-compatible agent)
- MCP Tools (
buy-stock,sell-stock) for secure and structured actions - TypeScript SDK for strong typing and scalable architecture
- StdioServerTransport for low-latency communication between AI and backend
Tech Stack
- Model Context Protocol (MCP)
- Zerodha Kite Connect API
- TypeScript
- StdioServerTransport (MCP SDK)
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.