TradingAgents MCPMode
TradingAgents-MCPmode 是一个创新的多智能体交易分析系统，集成了 Model Context Protocol (MCP) 工具，实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作，提供全面的市场分析、投资建议和风险管理。
What is TradingAgents MCPMode?
TradingAgents MCPMode is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to tradingagents-mcpmode 是一个创新的多智能体交易分析系统，集成了 model context protocol (mcp) 工具，实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作，提供全面的市场分析、投资建议和风险管理。
TradingAgents-MCPmode 是一个创新的多智能体交易分析系统，集成了 Model Context Protocol (MCP) 工具，实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作，提供全面的市场分析、投资建议和风险管理。
This server falls under the Finance & Fintech category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- TradingAgents-MCPmode 是一个创新的多智能体交易分析系统，集成了 Model Context Pro
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx tradingagents-mcpmodeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use TradingAgents MCPMode
TradingAgents-MCPmode is a multi-agent trading analysis system that integrates the Model Context Protocol to enable AI-driven stock research and investment decision workflows. The system orchestrates 15 specialized agents covering seven analysis dimensions — company overview, market data, sentiment, news, fundamentals, shareholder analysis, and product research — with configurable debate rounds for bullish/bearish and risk perspectives. It supports US stocks, Chinese A-shares, and Hong Kong stocks, and exposes its agent pipeline through a Streamlit web interface as well as a command-line interface.
Prerequisites
- Python 3.8 or higher
- An OpenAI API key (or compatible API with OPENAI_BASE_URL configured)
- A Tushare token for Chinese/HK market data (optional, for A-share and HK stock analysis)
- pip and virtualenv or conda for Python environment management
- Git to clone the repository
Clone the repository
Clone the TradingAgents-MCPmode repository from GitHub and navigate into the project directory.
git clone https://github.com/guangxiangdebizi/TradingAgents-MCPmode.git
cd TradingAgents-MCPmodeInstall Python dependencies
Install all required packages from the requirements file. It is recommended to use a virtual environment to avoid conflicts with other Python projects.
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txtConfigure environment variables
Copy the example environment file and edit it with your API keys and workflow parameters. At minimum you need OPENAI_API_KEY and MODEL_NAME.
cp env.example .env
# Edit .env:
# OPENAI_API_KEY=your_openai_key
# OPENAI_BASE_URL=https://api.openai.com/v1
# MODEL_NAME=gpt-4
# MAX_DEBATE_ROUNDS=1
# MAX_RISK_DEBATE_ROUNDS=1Configure MCP tools
Edit mcp_config.json to point to your MCP finance data server. The default configuration uses the finvestai.top hosted finance MCP with a Tushare token for market data.
{
"mcpServers": {
"finance-mcp": {
"disabled": false,
"timeout": 600,
"transport": "streamable_http",
"url": "https://finvestai.top/mcp",
"headers": {"X-Tushare-Token": "your_tushare_token"}
}
}
}Launch the web interface
Start the Streamlit web app to access the full multi-agent analysis interface with checkboxes to enable/disable agents, sliders for debate rounds, and real-time progress monitoring.
streamlit run web_app.py
# Then open http://localhost:8501 in your browserRun an analysis from the command line
Alternatively, invoke a stock analysis directly from the terminal using the CLI interface.
python main.py -c "Analyze Apple stock AAPL and give a buy/sell recommendation"
# Or run interactively:
python main.pyTradingAgents MCPMode Examples
MCP configuration for the finance data server
The mcp_config.json file that connects TradingAgents to the finance MCP data source for market data retrieval.
{
"mcpServers": {
"finance-mcp": {
"disabled": false,
"timeout": 600,
"transport": "streamable_http",
"url": "https://finvestai.top/mcp",
"headers": {
"X-Tushare-Token": "your_tushare_token_here"
}
}
}
}Prompts to try
Analysis commands to enter into the Streamlit web interface or the CLI.
- "Analyze Tesla stock TSLA and give a buy/sell/hold recommendation"
- "Analyze Apple AAPL with focus on fundamentals and recent news sentiment"
- "Compare NVDA and AMD and tell me which is a better investment right now"
- "Analyze the A-share stock 600519 (Kweichow Moutai) for medium-term outlook"
- "What are the biggest risk factors for investing in Microsoft MSFT?"Troubleshooting TradingAgents MCPMode
Analysis fails with 'API rate limit exceeded' or OpenAI errors
Reduce concurrent load by setting MAX_CONCURRENT_ANALYSIS=1 in your .env file and reducing MAX_DEBATE_ROUNDS to 1. The system runs up to 6 parallel analyst agents which can hit rate limits on lower-tier OpenAI plans. Consider using a higher-capacity model tier or GPT-4o-mini for cost efficiency.
MCP finance tools return empty data or timeout
Check that your Tushare token in mcp_config.json is valid and has the required data permissions. The default timeout is 600 seconds; if you are on a slow connection increase it. Verify the finvestai.top MCP endpoint is reachable from your environment.
Streamlit app does not load or shows import errors
Ensure you activated the virtual environment before running 'streamlit run web_app.py'. If streamlit is not found, run 'pip install streamlit' explicitly. Check that all requirements.txt packages installed without errors.
Frequently Asked Questions about TradingAgents MCPMode
What is TradingAgents MCPMode?
TradingAgents MCPMode is a Model Context Protocol (MCP) server that tradingagents-mcpmode 是一个创新的多智能体交易分析系统，集成了 model context protocol (mcp) 工具，实现了智能化的股票分析和交易决策流程。系统通过多个专业化智能体的协作，提供全面的市场分析、投资建议和风险管理。 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install TradingAgents MCPMode?
Follow the installation instructions on the TradingAgents MCPMode GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with TradingAgents MCPMode?
TradingAgents MCPMode works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is TradingAgents MCPMode free to use?
Yes, TradingAgents MCPMode is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
TradingAgents MCPMode Alternatives — Similar Finance & Fintech Servers
Looking for alternatives to TradingAgents MCPMode? 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.
Vibe Trading
★ 8.1k'Vibe-Trading: Your Personal Trading Agent'
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.
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 TradingAgents MCPMode 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 TradingAgents MCPMode?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.