Este es un servidor de Protocolo de Contexto de Modelo (MCP) que proporciona datos bursátiles desde la API de Alpha Vantage. Permite a Claude y a otros clientes de MCP acceder a datos bursátiles históricos y en tiempo real.
Obtenga datos bursátiles intradiarios con intervalos personalizables
Obtenga datos bursátiles diarios
Generar alertas de stock basadas en movimientos de precios
Acceda a los datos bursátiles como recursos
Related MCP server: Alpha Vantage MCP Server
Node.js 16 o superior
Una clave API de Alpha Vantage (obtenga una gratis en Alpha Vantage )
Clonar este repositorio
Instalar dependencias:
npm installCree un archivo .env en el directorio raíz y agregue su clave API de Alpha Vantage:
ALPHA_VANTAGE_API_KEY=your_api_key_hereConstruya el código TypeScript:
npm run buildEjecutar el servidor:
npm startPara desarrollo con recarga automática:
npm run devPruebe el cliente API:
npm testPara utilizar este servidor MCP con Claude for Desktop:
Abrir Claude para escritorio
Vaya a Configuración > Desarrollador > Editar configuración
Agregue lo siguiente a su claude_desktop_config.json :
{
"mcpServers": {
"alpha-vantage": {
"command": "node",
"args": ["/absolute/path/to/dist/index.js"],
"env": {
"ALPHA_VANTAGE_API_KEY": "YOUR_API_KEY"
}
}
}
}Reemplace /absolute/path/to/dist/index.js con la ruta absoluta al archivo index.js creado.
Reiniciar Claude para escritorio
Obtiene datos bursátiles intradiarios para un símbolo específico.
Parámetros:
symbol (obligatorio): Símbolo bursátil (p. ej., IBM, AAPL)
interval (opcional): Intervalo de tiempo entre puntos de datos (1 min, 5 min, 15 min, 30 min, 60 min). Valor predeterminado: 5 min.
outputsize (opcional): Cantidad de datos a devolver (compacto: últimos 100 puntos de datos, completo: hasta 20 años de datos). Predeterminado: compacto
Obtiene datos diarios de acciones para un símbolo específico.
Parámetros:
symbol (obligatorio): Símbolo bursátil (p. ej., IBM, AAPL)
outputsize (opcional): Cantidad de datos a devolver (compacto: últimos 100 puntos de datos, completo: hasta 20 años de datos). Predeterminado: compacto
Analiza datos bursátiles para generar alertas basadas en movimientos de precios.
Parámetros:
symbol (obligatorio): Símbolo bursátil (p. ej., IBM, AAPL)
threshold (opcional): Umbral porcentual para alertas de movimiento de precios. Valor predeterminado: 5
Acceda a los datos de stock directamente como recurso.
Plantilla de URI: stock://{symbol}/{interval}
Parámetros:
symbol : Símbolo bursátil (por ejemplo, IBM, AAPL)
interval : Intervalo de tiempo (diario, 1 min, 5 min, 15 min, 30 min, 60 min). Predeterminado: diario
Ejemplo de uso en Claude:
¿Puedes analizar estos datos bursátiles: stock://AAPL/daily?
¿Qué opinas de estos datos: stock://MSFT/5min?
Instituto Tecnológico de Massachusetts (MIT)
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Stock symbol (e.g., IBM, AAPL) | |
| outputsize | No | Amount of data to return (compact: latest 100 data points, full: up to 20 years of data) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Stock symbol (e.g., IBM, AAPL) | |
| threshold | No | Percentage threshold for price movement alerts (default: 5) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| symbol | Yes | Stock symbol (e.g., IBM, AAPL) | |
| interval | No | Time interval between data points (default: 5min) | |
| outputsize | No | Amount of data to return (compact: latest 100 data points, full: up to 20 years of data) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get-daily-stock-dataget-stock-alertsget-stock-dataScored across 3 tools
The tools are highly ambiguous and overlapping. 'get-daily-stock-data' and 'get-stock-data' appear to serve nearly identical purposes, with no description to clarify differences. 'get-stock-alerts' might be distinct but lacks context, making it unclear how it differs from the data retrieval tools. This setup will likely cause frequent agent misselection.
The naming follows a consistent pattern with kebab-case and a 'get-' verb prefix across all tools, which is predictable and readable. However, the lack of descriptions prevents full evaluation of semantic consistency, but structurally, the naming is uniform.
With only 3 tools, this server feels under-scoped for a stock analysis domain, which typically requires more operations like historical data, indicators, or portfolio management. The count is too low to provide comprehensive coverage, limiting agent capabilities.
The tool set is severely incomplete for stock analysis. It lacks essential operations such as intraday data, technical indicators, company fundamentals, or search functions. With only basic data retrieval and alerts, agents will face dead ends and cannot perform meaningful analysis.
Alpha Vantage MCP — Stock market data, fundamentals, and earnings
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.
Twelve Data MCP: real-time & historical market data (stocks, crypto, forex, etc).
Stock market data for AI agents: real-time quotes, financials, options, SEC filings and news.
