AI Trading Agent

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "themacroeconomicdao-bybit-ai-trader": {
      "command": "node",
      "args": [
        "/Users/Gyber/GYBERNATY-ECOSYSTEM/TRADER-AGENT/bybit-mcp/build/index.js"
      ],
      "env": {
        "DEBUG": "false",
        "PYTHONPATH": "/Users/.../mcp_server",
        "BYBIT_API_KEY": "your_api_key_here",
        "BYBIT_TESTNET": "false",
        "BYBIT_API_SECRET": "your_api_secret_here"
      }
    }
  }
}

You deploy and run two MCP servers to empower an AI trading assistant that analyzes the Bybit market in real time, suggests entry opportunities, and executes actions after your confirmation. This setup combines real-time market analysis with trading operations, while keeping you in control of risk and decisions.

How to use

Launch each MCP server from your orchestration client and connect them to Cursor as two separate MCP endpoints. Use the analysis server to feed market insights and the trading server to initiate and monitor trades. You will issue natural language commands like “conduct a market scan and identify entry points” and “open the first suggested position”; the agent will respond with structured analysis and, after your confirmation, carry out actions.

How to install

Prerequisites you need to have installed on your machine before starting are Python and Node.js. You also need a Python virtual environment and access to Bybit API credentials.

cd /Users/Gyber/GYBERNATY-ECOSYSTEM/TRADER-AGENT
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Configuration and deployment notes

You will run two MCP servers in tandem. The first handles market data and analytics in Node.js, the second handles trading actions in Python. Store API keys securely and do not commit them to version control.

{
  "mcpServers": {
    "bybit_analysis": {
      "command": "node",
      "args": ["/Users/Gyber/GYBERNATY-ECOSYSTEM/TRADER-AGENT/bybit-mcp/build/index.js"],
      "env": {
        "BYBIT_API_KEY": "your_api_key_here",
        "BYBIT_API_SECRET": "your_api_secret_here",
        "BYBIT_TESTNET": "false",
        "DEBUG": "false"
      }
    },
    "bybit_trading": {
      "command": "python",
      "args": ["/Users/Gyber/GYBERNATY-ECOSYSTEM/TRADER-AGENT/mcp_server/full_server.py"],
      "env": {
        "PYTHONPATH": "/Users/Gyber/GYBERNATY-ECOSYSTEM/TRADER-AGENT/mcp_server"
      }
    }
  }
}

Security and credentials

Keep credentials out of code. Use environment variables and a secure secrets manager where possible. Never expose your API keys in logs or shared files.

Examples of usage

You can ask the agent to perform a market study and identify entry points. The agent will provide a detailed analysis and highlight opportunities with high probability, then you can command it to open a position. The system will monitor positions continuously and alert you when actions are needed.

Troubleshooting

If a server fails to start, verify that the requested files exist at the given paths, environment variables are set, and that the required runtimes (Node.js and Python) are installed and accessible in your shell.

Built by

VeilStrat

AI signals for GTM teams