OptionsFlow MCP Server
Servidor MCP de OptionsFlow
Un servidor de Protocolo de Contexto de Modelo (MCP) que ofrece análisis avanzado de opciones y evaluación de estrategias a través de Yahoo Finance. Permite a los LLM analizar cadenas de opciones, calcular griegas y evaluar estrategias básicas de opciones con métricas de riesgo integrales.
Características
Análisis de opciones
Procesamiento completo de datos de la cadena de opciones
Cálculo griego (delta, gamma, theta, vega, rho)
Análisis de volatilidad implícita
Cálculos de probabilidad
Métricas de riesgo/recompensa
Análisis de estrategia
Spreads de llamadas de crédito (CCS)
Spreads de crédito de venta (PCS)
Opciones de venta garantizadas con efectivo (CSP)
Llamadas cubiertas (CC)
Evaluación de la posición de los griegos
Análisis de liquidez
Cálculo de métricas de riesgo
Gestión de riesgos
Análisis del diferencial entre oferta y demanda
Validación de volumen e interés abierto
Recomendaciones de tamaño de posición
Cálculos de pérdida máxima
Estimaciones de probabilidad de ganancias
Related MCP server: MCP Yahoo Finance
Instalación
# Install dependencies
pip install -r requirements.txt
# Clone the repository
git clone https://github.com/twolven/mcp-optionsflow.git
cd mcp-optionsflowUso
Agregue a su configuración de Claude: En su claude-desktop-config.json , agregue lo siguiente a la sección mcpServers :
{
"mcpServers": {
"optionsflow": {
"command": "python",
"args": ["path/to/optionsflow.py"]
}
}
}Reemplace "path/to/optionsflow.py" con la ruta completa donde guardó el archivo optionsflow.py.
Herramientas disponibles
analyze_basic_strategies
{
"symbol": str, # Required: Stock symbol
"strategy": str, # Required: "ccs", "pcs", "csp", or "cc"
"expiration_date": str, # Required: "YYYY-MM-DD"
"delta_target": float, # Optional: Target delta for CSP/CC (default: 0.3)
"width_pct": float # Optional: Width for spreads (default: 0.05)
}Formato de respuesta al análisis de estrategia
{
"symbol": str,
"strategy": str,
"current_price": float,
"expiration": str,
"days_to_expiration": int,
"analysis": {
# Credit Call Spread / Put Credit Spread
"strikes": {
"short_strike": float,
"long_strike": float
},
"metrics": {
"credit": float,
"max_loss": float,
"max_profit": float,
"probability_of_profit": float,
"risk_reward_ratio": float
},
"greeks": {
"net_delta": float,
"net_theta": float,
"net_gamma": float
}
# Cash Secured Put
"strike": float,
"metrics": {
"premium": float,
"max_loss": float,
"assigned_cost_basis": float,
"return_if_otm": float,
"downside_protection": float
},
"greeks": {
"delta": float,
"theta": float,
"gamma": float
}
# Covered Call
"strike": float,
"metrics": {
"premium": float,
"max_profit": float,
"max_profit_percent": float,
"upside_cap": float,
"premium_yield": float
},
"greeks": {
"position_delta": float,
"theta": float,
"gamma": float
}
}
}Requisitos
Python 3.12+
mcp
yfinanzas
pandas
Numpy
escipión
Limitaciones
Datos procedentes de Yahoo Finance con posibles retrasos.
La disponibilidad de datos de opciones depende del horario del mercado.
Límites de tarifas basados en las restricciones de la API de Yahoo Finance
Los cálculos griegos son teóricos y se basan en el modelo de Black-Scholes.
El riesgo de asignación temprana no se tiene en cuenta en los cálculos de probabilidad
Contribuyendo
¡Agradecemos sus contribuciones! No dude en enviar una solicitud de incorporación de cambios.
Licencia
Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.
Autor
Todd Wolven - ( https://github.com/twolven )
Expresiones de gratitud
Construido con el Protocolo de Contexto de Modelo (MCP) de Anthropic
Datos proporcionados por Yahoo Finance
Desarrollado para su uso con Claude de Anthropic
Available Tools
1 toolanalyze_basic_strategiesB
Analyze one legacy options strategy using executable quotes and European Black-Scholes estimates.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Yahoo Finance ticker symbol | |
| strategy | Yes | Options strategy: call credit spread, put credit spread, cash-secured put, or covered call | |
| width_pct | No | Target spread width as a fraction of the short strike | |
| delta_target | No | Absolute target delta for CSP/CC selection | |
| expiration_date | Yes | Expiration date in YYYY-MM-DD format |
Output Schema
| Name | Required | Description |
|---|---|---|
| data | Yes | |
| success | Yes | |
| provider | Yes | |
| warnings | Yes | |
| timestamp | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. It does add useful context by specifying that the analysis uses executable quotes and European Black-Scholes estimates, implying a read-only estimation nature. However, it does not disclose limitations, what 'legacy' means, or any other behavioral traits such as data-source assumptions or scope constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, tightly written sentence that communicates the core action and method without filler. It is front-loaded with the main purpose and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The input schema and output schema cover parameter details and return structure, so the description does not need to explain those. However, lack of usage guidance and limited behavioral disclosure leave the description only minimally complete for an agent deciding when and how to invoke it confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 100% of parameters with descriptions, so the baseline is 3. The description does not add parameter-level meaning beyond the schema; it only frames the overall pricing/analysis methodology. No compensation is needed, but no extra value is provided either.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a clear verb ('Analyze') and a specific resource ('one legacy options strategy'), and adds method context ('executable quotes and European Black-Scholes estimates'). However, 'legacy' is not explained, and with no sibling tools listed there is no explicit differentiation from alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given about when to use this tool versus alternatives, nor any exclusions or prerequisites. The description only implies that the tool is for analyzing an options strategy, but it does not state conditions or compare to other possible approaches.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v2.0.0- First observed
analyze_basic_strategies
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusing it with others. The tool's purpose is clearly articulated.
The single tool name 'analyze_basic_strategies' follows a clear verb_noun pattern and is syntactically consistent. There are no other names to create inconsistency.
One tool feels very thin for a server named 'OptionsFlow', which implies a broader range of options-related functionality. However, if the intended scope is strictly basic strategy analysis, the single tool is borderline acceptable.
The server only covers basic strategy analysis, leaving gaps for advanced strategies, other analytical features, or workflow operations. Agents needing additional options functionality will hit dead ends.
Maintenance
Related MCP Connectors
Financial data MCP server for Claude, ChatGPT, Cursor and Codex. Real-time stock quotes, financial statements, options flow, SEC filings, insider trades, 13F holdings, macro data and market news from gloom.sh, the open-source Bloomberg Terminal alternative.
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Production MCP server for US equity and options intelligence: real-time IV radar, Monte Carlo simulation, options pressure, strategy backtesting, AI prediction, pre-trade risk analysis, and automated stock research reports.
Related MCP Servers
- AlicenseBqualityBmaintenanceA Model Context Protocol server providing real-time stock data and options analysis through Yahoo Finance, enabling LLMs to access market data, analyze stocks, and evaluate options strategies.327MIT
- AlicenseBqualityAmaintenanceA Model Context Protocol server that enables interaction with Yahoo Finance to retrieve stock pricing, company information, and historical financial data through natural language queries.211,063 PyPI28MIT
- AlicenseCqualityNot gradedmaintenanceA Model Context Protocol server that provides tools for interacting with Yahoo Finance, allowing users to retrieve stock prices, company information, and perform financial data comparisons.11MIT
- AlicenseCqualityDmaintenanceA Model Context Protocol server providing comprehensive financial data from Yahoo Finance, allowing users to retrieve detailed stock information, financial statements, options data, and market news.34MIT