angel-one

The Angel One MCP Server provides a Model Context Protocol (MCP) interface to access Indian equity markets, commodities, and derivatives through Angel One's SmartAPI. It exposes a range of trading and market data capabilities, including portfolio management (view holdings, positions, RMS limits), trading operations (place/modify/cancel orders, view order books, create GTT rules), and market data (real-time LTP, OHLC historical data, instrument search, top movers, and PCR). Advanced features include option Greeks, position conversions, brokerage estimation, automated TOTP-based authentication, error handling, and safety/dry-run controls. You can interact with the server via the MCP to manage your trading workflow programmatically and integrate trading automation into your tools and dashboards.

To use the server, run the MCP endpoint as configured in the mcpServers section (angel-one-trading in the example). Your MCP-enabled client can send standard MCP requests to retrieve portfolio data, place or modify orders, fetch market data, and run analytics. The environment supports both development testing and production scenarios, with security features like TOTP authentication and configurable dry-run mode to simulate trades without live impact.

Prerequisites:

• Python 3.8 or newer
• Access to Angel One SmartAPI credentials (API key, client code, password, and TOTP secret)
• Git installed

Installation steps:

1. Clone the repository:

git clone https://github.com/YOUR_USERNAME/angel-one-mcp-server.git
cd angel-one-mcp-server

2. Create and activate a virtual environment (optional but recommended):

python -m venv venv
# On Windows
.
venv\Scripts\activate
# On macOS/Linux
source venv/bin/activate

3. Install dependencies:

pip install -r requirements.txt

4. Install the package in development mode (if applicable to your setup):

pip install -e .

5. Run the MCP server using the example configuration:

# Example (adjust module name if different):
python -m angel_one_mcp.server

6. Verify the server is running and accessible via the MCP interface at the configured port (default as per your setup).

Tips and notes:

• Use environment variables to keep sensitive credentials out of configuration files (ANGEL_ONE_API_KEY, ANGEL_ONE_CLIENT_CODE, ANGEL_ONE_PASSWORD, ANGEL_ONE_TOTP_SECRET).
• The server supports a dry-run mode to test trading workflows without executing real orders.
• Ensure your Python environment has access to the Angel One SmartAPI and that your API credentials are valid and TOTP is configured.
• If you encounter authentication issues, check that the TOTP secret is correctly configured and that time-based tokens are synchronized.
• Review logs for detailed error messages and enable verbose logging if troubleshooting is needed.
• For production deployments, consider containerizing the service (Docker) or orchestrating with a process manager (systemd, PM2-like tooling for Python wrappers) for reliability and restarts.