Vibe Trading
'Vibe-Trading: Your Personal Trading Agent'
What is Vibe Trading?
Vibe Trading is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 'vibe-trading: your personal trading agent'
'Vibe-Trading: Your Personal Trading Agent'
This server falls under the Finance & Fintech category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 'Vibe-Trading: Your Personal Trading Agent'
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx vibe-tradingConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Vibe Trading
Vibe Trading is a personal AI trading agent platform that combines 31 built-in agent tools, 77 finance skills, and a library of 452 pre-built alpha factors with an MCP server interface for natural language interaction. It supports backtesting strategies, analyzing market data, running swarm multi-agent research teams, and connecting to live broker accounts — all through conversational prompts — making sophisticated quantitative finance accessible without writing raw code.
Prerequisites
- Python 3.10+ installed
- pip for installing the vibe-trading-ai package
- An LLM API key for your chosen provider (e.g., OPENAI_API_KEY, DEEPSEEK_API_KEY, or GROQ_API_KEY)
- Optional: a Tushare token (TUSHARE_TOKEN) for A-share market data; falls back to AKShare without it
- An MCP-compatible client such as Claude Desktop for MCP server usage
Install Vibe Trading
Install the package from PyPI using pip. This installs the CLI tools, MCP server, and all financial analysis dependencies.
pip install vibe-trading-aiConfigure environment variables
Create an agent/.env file with your LLM provider settings and optional data source tokens.
# agent/.env
LANGCHAIN_PROVIDER=openrouter
OPENROUTER_API_KEY=your-api-key-here
OPENROUTER_BASE_URL=https://openrouter.ai/api/v1
LANGCHAIN_MODEL_NAME=deepseek/deepseek-chat
TUSHARE_TOKEN=your-tushare-token-optional
TIMEOUT_SECONDS=120
VIBE_TRADING_DATA_CACHE=trueTest the installation with the interactive TUI
Launch the interactive terminal UI to confirm the installation is working before setting up the MCP server.
vibe-tradingAdd the Vibe Trading MCP server to your client configuration
Configure Claude Desktop or another MCP client to use vibe-trading-mcp as the server command.
{
"mcpServers": {
"vibe-trading": {
"command": "vibe-trading-mcp",
"env": {
"LANGCHAIN_PROVIDER": "openrouter",
"OPENROUTER_API_KEY": "your-api-key-here",
"OPENROUTER_BASE_URL": "https://openrouter.ai/api/v1",
"LANGCHAIN_MODEL_NAME": "deepseek/deepseek-chat",
"TIMEOUT_SECONDS": "120"
}
}
}
}Restart your client and run your first backtest
Restart Claude Desktop to connect to the Vibe Trading MCP server. Ask it to run a strategy backtest or fetch market data.
Vibe Trading Examples
Client configuration
Claude Desktop config block for the Vibe Trading MCP server with LLM provider settings.
{
"mcpServers": {
"vibe-trading": {
"command": "vibe-trading-mcp",
"env": {
"LANGCHAIN_PROVIDER": "openrouter",
"OPENROUTER_API_KEY": "your-openrouter-api-key",
"OPENROUTER_BASE_URL": "https://openrouter.ai/api/v1",
"LANGCHAIN_MODEL_NAME": "deepseek/deepseek-chat",
"TIMEOUT_SECONDS": "120",
"VIBE_TRADING_DATA_CACHE": "true"
}
}
}
}Prompts to try
Example prompts for strategy backtesting, market analysis, and portfolio research using Vibe Trading.
- "Backtest a 20/50 day moving average crossover strategy on AAPL over the past 2 years."
- "Fetch current market data for the CSI 300 index and identify the top 5 momentum stocks."
- "Run the alpha101 factor library on the S&P 500 universe and show the top-performing factors."
- "Analyze my uploaded trades CSV and extract the strategy rules I seem to be following."
- "Start an investment committee swarm to debate whether TSLA is a buy at current prices."
- "What are the current positions and P&L in my connected trading account?"Troubleshooting Vibe Trading
LLM API call times out during backtesting
Increase TIMEOUT_SECONDS in your .env or MCP config (e.g., TIMEOUT_SECONDS=240). Backtesting with long historical periods or complex factor calculations can take longer than the default 120-second timeout.
Market data fetch fails or returns empty results
Vibe Trading falls back to AKShare if no TUSHARE_TOKEN is provided, but AKShare has rate limits. Enable data caching with VIBE_TRADING_DATA_CACHE=true to avoid repeated fetches. For A-share data, provide a valid TUSHARE_TOKEN from tushare.pro.
vibe-trading-mcp command not found after installation
Ensure the pip install completed successfully and that your Python scripts directory is on your PATH. Try running 'python -m vibe_trading.mcp' as an alternative. If using a virtual environment, activate it before running the command.
Frequently Asked Questions about Vibe Trading
What is Vibe Trading?
Vibe Trading is a Model Context Protocol (MCP) server that 'vibe-trading: your personal trading agent' It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Vibe Trading?
Follow the installation instructions on the Vibe Trading GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Vibe Trading?
Vibe Trading works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Vibe Trading free to use?
Yes, Vibe Trading is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Vibe Trading Alternatives — Similar Finance & Fintech Servers
Looking for alternatives to Vibe Trading? Here are other popular finance & fintech servers you can use with Claude, Cursor, and VS Code.
ValueCell
★ 10.7kValueCell is a community-driven, multi-agent platform for financial applications.
Quantdinger
★ 6.2kAI quantitative trading platform for crypto, stocks, and forex with backtesting, live trading, market data, and multi-agent research.vibe-trading ,trading-agents,ai-trader,ai-trading
TradingView
★ 2.8kReal-time crypto & stock screening, advanced technical indicators, Bollinger Bands intelligence, candlestick patterns + native Claude Desktop integration. Multi-exchange (Binance, KuCoin, Bybit+). Open-source AI trading infrastructure.
Financial Datasets
★ 2.1kProvides access to comprehensive financial data including income statements, balance sheets, cash flow statements, stock prices, company news, SEC filings, and cryptocurrency information with built-in financial ratio analysis.
Stripe
★ 1.6kThe Stripe Model Context Protocol server allows you to integrate with Stripe APIs through function calling. This protocol supports various tools to interact with different Stripe services.
Open Trading API
★ 1.4kKorea Investment & Securities Open API Github
Browse More Finance & Fintech MCP Servers
Explore all finance & fintech servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Vibe Trading in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Vibe Trading?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.