Trade-mcp
Trade-MCP
Documentation
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.
Features
- 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 `.env` file for security.
- Extensible: Easily add new tools or resources for more trading actions.
Setup
1. Clone the Repository
git clone
cd Trade-MCP2. Create and Activate a Virtual Environment
uv venv
.venv\Scripts\activate # On Windows
# or
source .venv/bin/activate # On Linux/Mac3. Install Dependencies
uv pip install -r requirements.txt
# or, if using pyproject.toml:
uv pip install .4. Configure Environment Variables
Create a `.env` file in the project root:
API_KEY=your_zerodha_api_key
API_SECRET=your_zerodha_api_secret5. Get Your Zerodha Access Token
To use the Zerodha API, you need an access token. Follow these steps:
1. Get Your API Key and Secret
2. Generate the Login URL
In a Python shell or script, run:
from kiteconnect import KiteConnect
kite = KiteConnect(api_key="your_api_key")
print(kite.login_url())3. Extract the `request_token`
`http://localhost:8000/?request_token=REQUEST_TOKEN_HERE&action=login&status=success`
4. Exchange the `request_token` for an `access_token`
In a Python shell or script, run:
data = kite.generate_session("REQUEST_TOKEN_HERE", api_secret="your_api_secret")
print(data["access_token"])5. Set the Access Token
Usage
Run the MCP Server
uv run --with mcp[cli] mcp run server.pyOr, if MCP CLI is installed in your environment:
mcp run server.pyClaude Desktop Integration
1. Add a server entry in your `claude_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
]
}
}
}2. Restart Claude Desktop.
3. The tools will appear in Claude's tool list.
Exposed Tools
- `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.
Extending
To add a new tool, define a function in `server.py` and decorate it with `@mcp.tool()`:
@mcp.tool()
def my_tool(...):
...License
MIT License
Frequently asked questions
What is Trade-mcp?
Trade-mcp is Trade-MCP
How do I install Trade-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is Trade-mcp open source?
Yes — it is hosted on GitHub at https://github.com/SamarJyoti496/Trade-mcp.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP