A free, professional, open-source financial analysis and quantitative trading MCP server. It lets you deploy a local financial MCP service with one command, using a departmental architecture that simulates a real financial firm’s operations. It supports traditional indicators, price action analysis, economic calendar, fundamentals, and news integration—providing seamless interaction with LLMs and algorithmic trading.

✨ Features

  • 🚀 One-click deployment: Quickly spin up a local financial MCP service
  • 🏢 Departmental architecture: Simulates real-world financial company departments
  • 📊 Comprehensive analysis: Traditional technical indicators + price action analysis
  • 📅 Real-time data: Economic calendar, fundamentals, and news integration
  • 🤖 AI integration: Interfaces optimized for LLMs
  • ⚡ High performance: Real-time streaming OHLC data processing
  • 🔧 Extensible: Support for custom MCP services

GitHub

1. Installation

  • Recommended (PyPI):
  pip install finance-trading-ai-agents-mcp

2. Fastest path to run (Python)

Save the following as main.py and run it:

  from finance_trading_ai_agents_mcp import mcp_run
from finance_trading_ai_agents_mcp.examples.env_example import get_example_env

if __name__ == "__main__":
    get_example_env()  # write example environment variables
    mcp_run()          # start the MCP service

After it starts, open your browser at: http://127.0.0.1:11999/

Tip: You need a free AITRADOS_SECRET_KEY to access financial data → https://www.aitrados.com/

Homepage image

3. Command-line (CLI) one-liners

  • Show help:
  finance-trading-ai-agents-mcp --help
  • Quick start (minimal config):
  finance-trading-ai-agents-mcp --env-config {"DEBUG":"1","AITRADOS_SECRET_KEY":"YOUR_SECRET_KEY"}
  • Specify port:
  python -m finance_trading_ai_agents_mcp -p 9000 --env-config {"DEBUG":"1","AITRADOS_SECRET_KEY":"YOUR_SECRET_KEY"}
  • Use a custom MCP capability file:
  python -m finance_trading_ai_agents_mcp -c finance_trading_ai_agents_mcp/examples/addition_custom_mcp_examples/addition_custom_mcp_example.py --env-config {"DEBUG":"1","AITRADOS_SECRET_KEY":"YOUR_SECRET_KEY"}

4. Required environment configuration (minimal)

Create a .env file in the project root (or pass values via –env-config):

  # Debug
DEBUG=true
# Get for free at https://www.aitrados.com/
AITRADOS_SECRET_KEY=YOUR_SECRET_KEY

# Max number of OHLC rows for LLM output only (does not affect strategy calculations)
OHLC_LIMIT_FOR_LLM=30
# Rename the column name from interval to timeframe (example)
RENAME_COLUMN_NAME_MAPPING_FOR_LLM=interval:timeframe,
# Minimal columns to provide to the LLM
OHLC_COLUMN_NAMES_FOR_LLM=timeframe,close_datetime,open,high,low,close,volume

Advanced options (optional):

  • LIVE_STREAMING_OHLC_LIMIT defaults to 150; if you need long-period indicators like MA200, increase it appropriately.

5. A few advanced steps (optional)

  • Custom MCP services and functions:
  from finance_trading_ai_agents_mcp import mcp_run
from finance_trading_ai_agents_mcp.examples.env_example import get_example_env

if __name__ == "__main__":
    get_example_env()
    from finance_trading_ai_agents_mcp.examples.addition_custom_mcp_examples.addition_custom_mcp_example import AdditionCustomMcpExample
    AdditionCustomMcpExample()
    mcp_run()
  • Reuse real-time WebSocket data + MCP simultaneously: see examples/run_mcp_examples/run_mcp_with_callback_real_time_websocks_data_example.py

6. Documentation and examples

— You’re all set. Start the service and let AI and real-time financial data work seamlessly in your workflow.