Kite MCP Trading Server
An MCP server for Zerodha Kite Connect that enables AI agents to execute trades, manage portfolios, fetch market data, and perform technical and fundamental analysis.
README
Kite MCP Trading Server
<p align="center"> <img src="./banner.png" alt="Kite MCP Server Banner" width="100%"> </p> A powerful Model Context Protocol (MCP) Server built with Bun + TypeScript for Zerodha Kite Connect.
This server enables AI agents, automation workflows, and trading applications to interact with Zerodha accounts for:
- Order Execution
- Portfolio Management
- Market Data Retrieval
- Technical Analysis
- Fundamental Analysis
Features
Trading Operations
- Place Buy Orders
- Place Sell Orders
- Modify Existing Orders
- Cancel Orders
- View Order History
- Fetch Active Orders
Portfolio Management
- Get Holdings
- Get Positions
- Calculate Profit & Loss (PnL)
Market Data
- Live Quotes
- Last Traded Price (LTP)
- Multiple Instrument Support
Technical Analysis
- EMA 20
- EMA 50
- RSI 14
- Trend Detection
- Buy / Sell / Hold Signals
Fundamental Analysis
- P/E Ratio Analysis
- Price to Book Ratio
- Return on Equity (ROE)
- Debt to Equity
- Profit Margins
- Earnings Growth
Technologies Used
Runtime & Language
- Bun
- TypeScript
Trading APIs
- Zerodha Kite Connect API
- Yahoo Finance API
MCP
- Model Context Protocol (MCP)
- MCP SDK
- MCP Server
Validation
- Zod
- JSON Schema
Architecture
Claude Desktop / Cursor / OpenAI
│
▼
Kite MCP Server
(Bun + TypeScript)
│
▼
Zerodha Kite Connect
│
▼
Indian Stock Market
Installation
git clone https://github.com/BrextherFx/kite-mcp-server.git
cd kite-mcp-server
bun install
Environment Variables
Create a .env file:
KITE_API_KEY=
KITE_API_SECRET=
KITE_REQUEST_TOKEN=
KITE_ACCESS_TOKEN=
Running the Server
Development:
bun run dev
Generate Token:
bun run gen
Production:
bun run start
Zerodha Kite Developer Setup
Step 1: Create a Zerodha Trading Account
Open:
https://zerodha.com/open-account
Login:
https://kite.zerodha.com
Step 2: Create Kite Developer Account
https://developers.kite.trade/signup
Create your developer account.
Step 3: Create Application
Open:
https://developers.kite.trade
Create a new application.
Example:
App Name: Kite MCP Server
Redirect URL: http://localhost:3000/callback
Save and collect:
API Key
API Secret
Step 4: Configure IP Whitelist
Find your public IP:
https://ifconfig.me
Add the IP in:
Developer Console
└── Profile
└── IP Whitelist
Step 5: Generate Request Token
bun run gen
Login using the generated URL.
Copy:
request_token=xxxxxxxx
Step 6: Generate Access Token
Store it inside .env:
KITE_ACCESS_TOKEN=xxxxxxxx
Claude Desktop Setup
Open:
%APPDATA%\Claude\claude_desktop_config.json
Add:
{
"mcpServers": {
"kite": {
"command": "bun",
"args": [
"run",
"C:/Projects/kite-mcp/index.ts"
]
}
}
}
Restart Claude Desktop.
MCP Tools
| Tool | Description |
|---|---|
| buy-stock | Place buy order |
| sell-stock | Place sell order |
| modify-order | Modify order |
| cancel-order | Cancel order |
| get-orders | Get orders |
| get-holdings | Get holdings |
| get-positions | Get positions |
| get-quote | Get live quote |
| get-ltp | Get LTP |
| get-margins | Get margins |
| get-pnl | Calculate PnL |
| analyze-stock | Technical + Fundamental Analysis |
Roadmap
- [ ] WebSocket Live Market Data
- [ ] Option Chain Analysis
- [ ] AI Trade Recommendations
- [ ] Portfolio Risk Analysis
- [ ] Historical Backtesting
Contributing
Contributions are welcome.
Feel free to open Issues or Pull Requests.
License
MIT License
Author
Momin Saad (BrextherFx)
Software Developer • AI Builder • Automation Enthusiast
🌐 Website: brextherfx.site
💻 GitHub: BrextherFx
Made with ❤️ by BrextherFx.
⭐ If you find this project useful, consider giving it a star.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.