OptionsFlow MCP Server

by twolven

35 stars
276 downloads
Not rated
GitHub

About

An MCP server providing advanced options analysis through Yahoo Finance, supporting Greeks calculations, strategy evaluation (CCS/PCS/CSP/CC), and risk metrics. Built for MCP with Claude.ai.

Details

Author
twolven
GitHub stars
35
Downloads
276
Categories
Other

- Complete options chain data processing and Greeks calculation
- Strategy analysis for credit spreads, secured puts, and covered calls
- Risk management with bid-ask spread and volume validation
- Implied volatility analysis and probability calculations
- Position Greeks evaluation and liquidity analysis
- Maximum loss and probability of profit estimates

Install dependencies (pip install -r requirements.txt), clone the repository, then add the server to your Claude configuration in claude-desktop-config.json with command: "python" and args: ["path/to/optionsflow.py"]. Use the analyze_basic_strategies tool by providing a stock symbol, strategy type (ccs, pcs, csp, cc), expiration date, and optional parameters like delta target or width percentage.

OptionsFlow MCP Server

A Model Context Protocol (MCP) server providing advanced options analysis and strategy evaluation through Yahoo Finance. Enables LLMs to analyze options chains, calculate Greeks, and evaluate basic options strategies with comprehensive risk metrics.

Features

Options Analysis

- Complete options chain data processing - Greeks calculation (delta, gamma, theta, vega, rho) - Implied volatility analysis - Probability calculations - Risk/reward metrics

Strategy Analysis

- Credit Call Spreads (CCS) - Put Credit Spreads (PCS) - Cash Secured Puts (CSP) - Covered Calls (CC) - Position Greeks evaluation - Liquidity analysis - Risk metrics calculation

Risk Management

- Bid-ask spread analysis - Volume and open interest validation - Position sizing recommendations - Maximum loss calculations - Probability of profit estimates

Installation

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.