Trade-MCP

A modular trading automation project using Zerodha Kite Connect and MCP (Modular Command Platform) for tool-based and resource-based automation. This project exposes trading actions (like placing orders and fetching holdings) as MCP tools, making them accessible to Claude Desktop and other MCP-compatible clients.

- Zerodha Integration:Place buy/sell orders and fetch holdings using the Kite Connect API.
- MCP Tools:Expose trading actions as callable tools for automation and AI agents.
- Environment-based Secrets:API keys and secrets are loaded from a.envfile for security.
- Extensible:Easily add new tools or resources for more trading actions.

git clone <your-repo-url> cd Trade-MCP

2. Create and Activate a Virtual Environment

uv venv .venv\Scripts\activate # On Windows # or source .venv/bin/activate # On Linux/Mac

uv pip install -r requirements.txt # or, if using pyproject.toml: uv pip install .

API_KEY=your_zerodha_api_key API_SECRET=your_zerodha_api_secret

To use the Zerodha API, you need anaccess token. Follow these steps:

- Obtain these from theZerodha developer console.

from kiteconnect import KiteConnect kite = KiteConnect(api_key="your_api_key") print(kite.login_url())

data = kite.generate_session("REQUEST_TOKEN_HERE", api_secret="your_api_secret") print(data["access_token"])

- Replace"REQUEST_TOKEN_HERE"and"your_api_secret"with your actual values.
- The printed value is youraccess_token.

- You can set this as an environment variable or use it directly in your code as needed.

uv run --with mcp[cli] mcp run server.py

Or, if MCP CLI is installed in your environment:
-

Add a server entry in yourclaude_desktop_config.json:

{ "mcpServers": { "Trade-MCP": { "command": "uv.EXE", # Exact Path to uv executable "args": [ "run", "--with", "mcp[cli]", "mcp", "run", "server.py" # Exact Path to your server script ] } } }

The tools will appear in Claude's tool list.

- add(a: int, b: int): Add two numbers.
- place_zerodha_buy_order(symbol: str, quantity: int): Place a buy order.
- place_zerodha_sell_order(symbol: str, quantity: int): Place a sell order.
- get_zerodha_holdings(): Get all holdings from Zerodha.

To add a new tool, define a function inserver.pyand decorate it with@mcp.tool():

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Managed MCP server for Bybit perpetual futures trading. Isolated sub-accounts, built-in risk management, 12 trading tools.

Access real-time and historical token, wallet, and trading data from the Solana ecosystem via the Solana Tracker API.

Access financial data like stock prices, currency info, and insider trading data using the Synth Finance API.

Provides access to TakeProfit.com's Indie documentation and tooling — a Python-based scripting language for building custom cloud indicators and trading strategies on the TakeProfit platform.

50+ pay-per-call APIs for AI agents via HTTP 402 crypto micropayments. $0.001–$0.12 per call with USDC and USDm.

Deterministic macro regime engine for AI trading agents — RISK_ON / NEUTRAL / RISK_OFF / STRESS with transparent scoring rules.

A quantitative analysis platform for Futu Securities, offering intelligent caching, technical analysis, and pattern recognition.

A high-performance MCP server for comprehensive options order flow analysis.

Complete MCP server for MT5: Through the MCP protocol, it allows [Trades, Orders, History, Graphic Objects, Terminal Logs, Compilation, etc.]

Integrates the xtquant quantitative trading platform with an AI assistant, enabling AI to access and operate quantitative trading data and functions.