angleone

This MCP server integrates Angel One's trading APIs to fetch history data and portfolio information through the Model Context Protocol. The angleone MCP server is exposed via the uv runner, which executes api.py in the specified project directory. After starting the MCP server with the provided configuration, clients can connect to the angleone server to request historical data, such as instrument-specific price history, and portfolio snapshots. The server leverages Angel One credentials (API_KEY, CLIENT_CODE, PASSWORD, PIN, and an optional TOKEN) to authenticate and retrieve data from Angel One's API endpoints, then returns the results in MCP-compatible messages for downstream processing.

To use, ensure you have a running MCP client configured to communicate with the angleone server. The server's endpoints will respond with data structures containing historical records and portfolio details, suitable for ingestion into analytics, dashboards, or backtesting workflows. If you need to update credentials, modify the test_credentials.py file (as described in the repository) or set the corresponding environment variables before launching api.py.

Prerequisites:

• Python 3.10
• Access to Angel One trading API credentials (API_KEY, CLIENT_CODE, PASSWORD, PIN, TOKEN optional)
• git

Installation steps:

1. Clone the repository and initialize submodules:

git clone https://github.com/yourusername/angelone-mcp.git
cd angelone-mcp
git submodule update --init --recursive

2. Create a Python virtual environment and activate it:

python3.10 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install uv (Python package runner) if not already installed, or run the provided installer:

curl -LsSf https://astral.sh/uv/install.sh | sh

4. Install Python dependencies from requirements.txt:

uv pip install -r requirements.txt

5. Prepare credentials by creating a credentials file as described (e.g., test_credentials.py) and populate API_KEY, CLIENT_CODE, PASSWORD, PIN, and optional TOKEN.
6. Start the API server via the MCP runner configuration (see the usage example in the repository):

# Example: using uv as in the README
uv --directory /Users/rohandoshi/Development/angelone-mcp run api.py

Notes and tips:

• Ensure Python 3.10 is used to match the project requirements.
• Maintain your Angel One credentials securely; avoid embedding them directly in code for production setups.
• The MCP configuration assumes api.py is the entry-point that serves the MCP-compatible API. Adjust the path if your setup differs.
• If you encounter connection or authentication issues, verify that the API_KEY, CLIENT_CODE, PASSWORD, PIN, and TOKEN (if used) are correct and that the Angel One API is reachable from your environment.
• If you modify the directory structure, update the --directory path in the MCP config accordingly.
• For debugging, check any logs produced by api.py or the uv runner for detailed error messages.