maverick-mcp

Overview of maverick-mcp

What it is

MaverickMCP is an open-source stock market MCP server that connects an AI assistant to Yahoo Finance data through yfinance. It runs locally on your computer with no API key required for core tools. The server stores your portfolio, watchlists, and trade journal in a local database. It is designed for educational and informational use and does not place orders or provide financial advice.

Key features

• Market data and technical analysis: get quotes, historical prices, fundamentals, RSI, MACD, and observed support and resistance levels.
• Stock screening: run bullish, bearish, and supply/demand screens over symbols you have loaded.
• Portfolio tracking: record positions, calculate average cost and profit or loss, review risk, manage watchlists, and keep a trade journal.
• Optional backtesting and research: test strategies on historical data, compare results, or research companies and sectors with source citations.
• The v1.2.1 release includes 38 core tools, 12 optional backtesting tools, and 3 optional research tools.

Use cases

• Educational and informational stock analysis using real market data.
• Personal portfolio tracking and trade journaling without broker integration.
• Backtesting trading strategies on historical data (with optional package).
• Researching companies and sectors with language model and web search (with optional package).

Getting started

Install Python 3.12 or later and uv. SQLite is included. bash git clone https://github.com/wshobson/maverick-mcp.git cd maverick-mcp uv sync cp .env.example .env For optional backtesting or research: bash uv sync --extra backtesting --extra research Connect your MCP client using STDIO: bash uv run --directory /absolute/path/to/maverick-mcp maverick-mcp --transport stdio Or run from a Git tag: bash uvx --from 'git+https://github.com/wshobson/[email protected]' maverick-mcp --transport stdio See the repository README for client configuration details.

License and pricing

The project is licensed under MIT and is open source.

Based on the project's public README and repository metadata.