Skip to main content
Glama
cds-id

MCP Server Boilerplate

by cds-id

Plantilla estándar del servidor MCP

Versión NPM del SDK TypeScript de MCP Licencia MIT

Una implementación de servidor estándar para el Protocolo de Contexto de Modelo (MCP), creado con TypeScript y Express.

Tabla de contenido

Related MCP server: MCP Server Scaffold

Descripción general

Este proyecto implementa un servidor que sigue el Protocolo de Contexto de Modelo (MCP), lo que permite a las aplicaciones proporcionar contexto para LLM de forma estandarizada. Incluye:

  • Un servidor MCP completamente configurado con opciones de transporte HTTP y stdio

  • Recursos de muestra, herramientas y sugerencias para demostrar la funcionalidad clave

  • Compatibilidad con TypeScript para seguridad de tipos y una mejor experiencia para el desarrollador

  • Integración expresa para la capa de transporte HTTP

Estructura del proyecto

mcp-server-boilerplate/
├── .env                  # Environment variables
├── .env.example          # Example environment variables
├── .gitignore            # Git ignore file
├── package.json          # Project dependencies and scripts
├── tsconfig.json         # TypeScript configuration
├── src/
│   ├── index.ts          # Main HTTP server entry point
│   ├── stdio.ts          # Stdio server entry point
│   ├── resources/        # MCP resources
│   │   ├── index.ts      # Resource registration
│   │   ├── infoResource.ts # Static info resource
│   │   └── greetingResource.ts # Dynamic greeting resource
│   ├── tools/            # MCP tools
│   │   ├── index.ts      # Tool registration
│   │   ├── calculatorTool.ts # Sample calculator tool
│   │   └── timestampTool.ts # Sample timestamp tool
│   └── prompts/          # MCP prompts
│       ├── index.ts      # Prompt registration
│       ├── greetingPrompt.ts # Sample greeting prompt
│       └── analyzeDataPrompt.ts # Sample data analysis prompt
└── dist/                 # Compiled JavaScript output

Empezando

Prerrequisitos

  • Node.js (v18 o posterior)

  • npm o hilo

Instalación

Clonar el repositorio e instalar las dependencias:

git clone https://github.com/yourusername/mcp-server-boilerplate.git
cd mcp-server-boilerplate
npm install

Variables de entorno

Copie el archivo de entorno de ejemplo y modifíquelo según sea necesario:

cp .env.example .env

Variables de entorno disponibles:

  • PORT : El puerto para el servidor HTTP (predeterminado: 3000)

  • NODE_ENV : Modo de entorno (desarrollo, producción)

  • Configuración de OAuth (si es necesario)

Ejecución del servidor

Servidor HTTP

Construya e inicie el servidor HTTP:

npm run build
npm start

Para desarrollo con reinicio automático:

npm run dev

El servidor estará disponible en http://localhost:3000/mcp (o el puerto especificado en su archivo .env).

Modo estudio

Para ejecutar el servidor en modo stdio (para herramientas de línea de comandos):

npm run start:stdio

Para desarrollo con reinicio automático:

npm run dev:stdio

Recursos

El texto estándar incluye estos recursos de ejemplo:

  1. Recurso de información estática : info://server

    • Proporciona información básica sobre el servidor.

  2. Recurso de saludo dinámico : greeting://{name}

    • Genera un saludo personalizado con el parámetro de nombre proporcionado

Para acceder a los recursos:

  • A través del protocolo MCP

  • Uso de una biblioteca de cliente MCP

Herramientas

El código estándar incluye estas herramientas de ejemplo:

  1. Calculadora : Realiza operaciones aritméticas básicas

    • Parámetros:

      • operation : Operación a realizar (sumar, restar, multiplicar, dividir)

      • a : Primer número

      • b : Segundo número

  2. Marca de tiempo : proporciona la hora actual en varios formatos

    • Parámetros:

      • format : Formato de salida (iso, unix, legible)

Indicaciones

El texto estándar incluye estos ejemplos:

  1. Saludo : crea un mensaje de saludo personalizado

    • Parámetros:

      • name : Nombre para saludar

      • formal : si se debe utilizar el estilo de saludo formal (opcional)

  2. Analizar datos : crea una solicitud para el análisis de datos

    • Parámetros:

      • data : Los datos a analizar

      • format : Formato de datos (json, csv, texto)

      • instructions : Instrucciones de análisis adicionales (opcional)

Ampliación del servidor

Añadiendo recursos

Para agregar un nuevo recurso:

  1. Crea un nuevo archivo en src/resources/ (por ejemplo, myResource.ts )

  2. Implemente su controlador de recursos

  3. Regístrelo en src/resources/index.ts

Ejemplo:

// myResource.ts
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';

export function myResource(server: McpServer): void {
  server.resource('my-resource', 'my-resource://path', async uri => ({
    contents: [
      {
        uri: uri.href,
        text: 'My resource content',
      },
    ],
  }));
}

// Then add to resources/index.ts
import { myResource } from './myResource.js';

export function registerResources(server: McpServer): void {
  // ...existing resources
  myResource(server);
}

Agregar herramientas

Para agregar una nueva herramienta:

  1. Crea un nuevo archivo en src/tools/ (por ejemplo, myTool.ts )

  2. Implemente su controlador de herramientas

  3. Regístrelo en src/tools/index.ts

Ejemplo:

// myTool.ts
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { z } from 'zod';

export function myTool(server: McpServer): void {
  server.tool('my-tool', { param: z.string() }, async ({ param }) => ({
    content: [
      {
        type: 'text',
        text: `Processed: ${param}`,
      },
    ],
  }));
}

// Then add to tools/index.ts
import { myTool } from './myTool.js';

export function registerTools(server: McpServer): void {
  // ...existing tools
  myTool(server);
}

Agregar indicaciones

Para agregar un nuevo mensaje:

  1. Crea un nuevo archivo en src/prompts/ (por ejemplo, myPrompt.ts )

  2. Implemente su controlador de indicaciones

  3. Regístrelo en src/prompts/index.ts

Ejemplo:

// myPrompt.ts
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { z } from 'zod';

export function myPrompt(server: McpServer): void {
  server.prompt('my-prompt', { topic: z.string() }, ({ topic }) => ({
    messages: [
      {
        role: 'user',
        content: {
          type: 'text',
          text: `Please explain ${topic} in simple terms.`,
        },
      },
    ],
  }));
}

// Then add to prompts/index.ts
import { myPrompt } from './myPrompt.js';

export function registerPrompts(server: McpServer): void {
  // ...existing prompts
  myPrompt(server);
}

Pruebas y depuración

Para probar su servidor MCP, puede utilizar:

  • La herramienta Inspector de MCP

  • Bibliotecas de cliente MCP

  • Solicitudes HTTP directas (para depuración)

Licencia

Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.

Available Tools

2 tools
calculateD
ParametersJSON Schema
NameRequiredDescriptionDefault
operationYes
aYes
bYes

TDQS

D1/5.0
Behavior1/5

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.

Conciseness1/5

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.

Completeness1/5

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.

Parameters1/5

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.

Purpose1/5

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.

Usage Guidelines1/5

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.

timestampD
ParametersJSON Schema
NameRequiredDescriptionDefault
formatNoiso

TDQS

D1/5.0
Behavior1/5

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.

Conciseness1/5

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.

Completeness1/5

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.

Parameters1/5

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.

Purpose1/5

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.

Usage Guidelines1/5

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.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updates
    • First observedcalculate
    • First observedtimestamp

TDQS

D1.7/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: 'calculate' suggests mathematical or computational operations, while 'timestamp' implies time-related functions. With no overlapping descriptions, there is no ambiguity between them.

Naming Consistency5/5

Both tool names follow a consistent pattern of using single, descriptive nouns in lowercase. There are no deviations in style or convention across the set.

Tool Count2/5

With only 2 tools, the server feels thin and under-scoped for a 'boilerplate' purpose, which typically implies a foundational or example set. This minimal count limits functionality and utility.

Completeness1/5

The server lacks descriptions, making it impossible to infer a clear domain or assess coverage. Without context, it appears severely incomplete, with no indication of what operations are supported or how they fit together.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • F
    license
    B
    quality
    D
    maintenance
    A basic starter project for building Model Context Protocol (MCP) servers that enables standardized interactions between AI systems and various data sources through secure, controlled tool implementations.
    2
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    A starter project designed to quickly build and deploy Model Context Protocol (MCP) servers using the TypeScript SDK and Zod for schema validation. It features example implementations for tools and resources, providing a solid foundation for custom MCP development and integration.
    -
  • F
    license
    Not graded
    quality
    D
    maintenance
    A minimal Model Context Protocol (MCP) server demonstrating the implementation of tools, resources, and prompts. It serves as a starter template built with the Smithery SDK for developing custom integrations.
    -