filtrix-mcp 0.1.0

MCP server for Filtrix — historical trading pattern analysis for AI agents

Filtrix MCP Server

MCP (Model Context Protocol) server that gives AI assistants access to Filtrix — a historical trading pattern discovery engine with 348K+ records and 255 filters spanning 5 years of data.

What can it do?

Tool	Description
run_backtest	Run a historical backtest with filters. Returns sample size, win rate, average move, percentiles.
screen_tickers	Find matching historical events. Returns date, symbol, price, gap, volume.
get_ticker_info	Get ticker metadata: company name, sector, market cap, exchange, employees.
list_filters	Discover all 255 available filter columns (gap, price, float, volume, etc.).

Quick Start

1. Get an API key

Sign up at filtrix.net, then generate an API key in your account settings.

2. Configure Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "filtrix": {
      "command": "uvx",
      "args": ["filtrix-mcp"],
      "env": {
        "FILTRIX_API_KEY": "flt_your_key_here"
      }
    }
  }
}

Config file location:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

3. Restart Claude Desktop

The Filtrix tools will appear automatically.

Usage Examples

Once configured, ask Claude things like:

• "What happens historically when a stock gaps up 30% with a float under 10M shares?"
• "Show me the last 20 stocks that gapped up over 50%"
• "Look up NVDA ticker info"
• "What filters are available for backtesting?"

Alternative: pip install

pip install filtrix-mcp

Then run manually:

export FILTRIX_API_KEY="flt_your_key_here"
filtrix-mcp

Environment Variables

Variable	Required	Default	Description
FILTRIX_API_KEY	Yes	—	Your Filtrix API key (starts with flt_)
FILTRIX_BASE_URL	No	https://filtrix.net	API base URL

Rate Limits

Tier	Daily Limit
Free	50 requests
Pro	1,000 requests

Limits reset at midnight ET.

Requirements

• Python 3.10+
• Active Filtrix account with API key