Get the FREE Ultimate OpenClaw Setup Guide →

prism-insight

AI-based stock analysis and trading system

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio dragon1086-prism-insight python stock_analysis_orchestrator.py --mode morning --no-telegram \
  --env OPENAI_API_KEY="your_openai_api_key_here" \
  --env PERPLEXITY_API_KEY="optional_perplexity_api_key_if_using_news_analysis"

How to use

PRISM-INSIGHT is an open-source AI-powered stock analysis and trading system that coordinates a team of 13+ specialized AI agents to detect surge stocks, generate analyst-grade reports, and support trading decisions. The server runs the stock analysis orchestrator which leverages GPT-5 for analysis, Claude Sonnet for translation and Telegram integration, and a multi-agent workflow to produce detailed reports and trading signals. You can run the MEC server in Python (recommended for development) or via Docker for production. To use, provide your OpenAI API key and any other credentials required by the configuration files. The system can generate US and Korean market insights, with reports saved locally as PDFs or output to configured channels in Telegram when enabled.

How to install

Prerequisites:

  • Python 3.10+ (or Docker for containerized deployment)
  • OpenAI API Key (and optional Perplexity API key for news analysis)

Option A: Python Installation

  1. Clone the repository and install dependencies git clone https://github.com/dragon1086/prism-insight.git cd prism-insight pip install -r requirements.txt

  2. Install Playwright for PDF generation python3 -m playwright install chromium

  3. Install the Perplexity MCP server (optional for news analysis) cd perplexity-ask && npm install && npm run build && cd ..

  4. Prepare configuration files cp mcp_agent.config.yaml.example mcp_agent.config.yaml cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml

    Edit mcp_agent.secrets.yaml with your OpenAI API key

    Edit mcp_agent.config.yaml with any credentials (e.g., KRX)

  5. Run analysis (Telegram not required for local runs) python stock_analysis_orchestrator.py --mode morning --no-telegram

Option B: Docker (Recommended for Production)

  1. Clone & Configure git clone https://github.com/dragon1086/prism-insight.git cd prism-insight cp mcp_agent.config.yaml.example mcp_agent.config.yaml cp mcp_agent.secrets.yaml.example mcp_agent.secrets.yaml

    Edit config files with your API keys

  2. Build & Run docker-compose up -d

  3. Optional: Run analysis manually inside container docker exec prism-insight-container python3 stock_analysis_orchestrator.py --mode morning --no-telegram

For full setup guidance, see docs/SETUP.md.

Additional notes

Notes and tips:

  • Environment variables: OPENAI_API_KEY is required to run the analysis. If you enable news analysis via Perplexity, set PERPLEXITY_API_KEY as well.
  • The system supports US and Korean markets and can output PDF reports to prism-us/pdf_reports/ by default when running locally.
  • If you use Docker, ensure docker-compose.yml is configured for production, and mount any required secret/config files into the container.
  • The quickstart mentions a docker-compose.quickstart.yml for a minimal containerized run; you can adapt that approach to your deployment as needed.
  • If you encounter Playwright issues for PDF generation, ensure Chromium is installed in the environment and that graphical dependencies are available (headless mode is typical).
  • The MCP integration expects a configuration file mcp_agent.config.yaml and secrets mcp_agent.secrets.yaml; keep these secure and do not commit to public repos.

Related MCP Servers

Sponsor this space

Reach thousands of developers