home / mcp / maverickmcp server

MaverickMCP Server

MaverickMCP - Personal Stock Analysis MCP Server

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "wshobson-maverick-mcp": {
      "url": "http://localhost:8003/mcp",
      "headers": {
        "LOG_LEVEL": "INFO",
        "REDIS_HOST": "localhost",
        "REDIS_PORT": "6379",
        "EXA_API_KEY": "YOUR_EXA_KEY",
        "DATABASE_URL": "sqlite:///maverick_mcp.db",
        "FRED_API_KEY": "YOUR_FRED_KEY",
        "OPENAI_API_KEY": "YOUR_OPENAI_KEY",
        "TAVILY_API_KEY": "YOUR_TAVILY_KEY",
        "TIINGO_API_KEY": "YOUR_TIINGO_KEY",
        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_KEY",
        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY"
      }
    }
  }
}

MaverickMCP is a personal FastMCP 2.0 server that delivers comprehensive stock analysis, technical indicators, backtesting, and portfolio tools directly to your MCP clients. It seeds a 520-stock S&P 500 database, supports multiple transports, and emphasizes fast development, smart caching, and local execution for individual traders and learners.

How to use

Connect to the MaverickMCP server from your MCP client to access 29+ financial analysis tools, backtesting, screening, and portfolio capabilities. You can run backtests, generate technical analysis, screen stocks against multiple strategies, and manage a personal portfolio with live P&L. Use the SSE transport for a stable, persistent connection, or the STDIO pathway for development work alongside a compatible client.

How to install

Prerequisites: you need Python 3.12 or newer and a modern Python package manager. You will also install uv for fast development, and you may install TA-Lib for advanced indicators. Optional caching with Redis and a database like PostgreSQL or SQLite is supported.

1) Install uv (recommended for fast startup and development) and set up the environment.

Step by step commands

# Prerequisites and quick setup
# 1) Install uv (recommended)
curl -LsSf https://astral.sh/uv/install.sh | sh

# 2) Install TA-Lib if you need advanced indicators
brew install ta-lib  # macOS
# For Windows/macOS, follow platform-specific TA-Lib installation steps as needed

# 3) Install Python dependencies and start the server
# Clone the project
git clone https://github.com/wshobson/maverick-mcp.git
cd maverick-mcp

# Install dev dependencies and seed data, then start
make dev

# The server will be available at:
# HTTP endpoint: http://localhost:8003/mcp/
# SSE endpoint: http://localhost:8003/sse/
# 520 S&P 500 stocks seeded on first run

# Optional: copy environment file and add your API keys
cp .env.example .env
# Edit .env to add TIINGO_API_KEY and any optional keys
"""
Note: The final startup command seeds the S&P 500 data on first run and starts the server in one combined step when using make dev.
"""

Connect to Claude Desktop with SSE

{
  "mcpServers": {
    "maverick-mcp": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "http://localhost:8003/sse/"]
    }
  }
}

Alternative: STDIO connection for development

{
  "mcpServers": {
    "maverick-mcp": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "-m",
        "maverick_mcp.api.server",
        "--transport",
        "stdio"
      ],
      "cwd": "/path/to/maverick-mcp"
    }
  }
}

Available tools

fetch_stock_data

Get historical stock data with intelligent caching and retrieval

fetch_stock_data_batch

Fetch data for multiple tickers simultaneously to speed up analysis

get_rsi_analysis

Calculate RSI values and generate buy/sell signals

get_macd_analysis

Compute MACD indicators and identify crossovers

get_support_resistance

Identify key price levels for potential breakouts

get_full_technical_analysis

Produce a comprehensive set of indicators and insights

portfolio_add_position

Add or update positions with automatic cost basis averaging

portfolio_get_my_portfolio

Return the current portfolio with live P&L calculations

portfolio_remove_position

Remove partial or full positions from the portfolio

portfolio_clear_portfolio

Clear all positions with a safety confirmation

get_maverick_stocks

Bullish momentum screening across 520 S&P 500 stocks

get_maverick_bear_stocks

Bearish setup screening based on pre-analyzed data

get_trending_breakout_stocks

Screen for strong uptrends with supply/demand analysis

run_backtest

Execute backtests using the VectorBT engine with multiple strategies

optimize_strategy

Walk-forward optimization and parameter tuning for strategies

get_backtest_report

Generate detailed HTML reports with visualizations of backtests

research_comprehensive

Full parallel research using multiple AI agents for deep analysis

research_company

Company-specific deep research with financial analysis

analyze_market_sentiment

Multi-source sentiment analysis with credibility tracking

coordinate_agents

Multi-agent supervisor for complex research orchestration