MCP Server Boilerplate
Plantilla estándar del servidor MCP
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 outputEmpezando
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 installVariables de entorno
Copie el archivo de entorno de ejemplo y modifíquelo según sea necesario:
cp .env.example .envVariables 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 startPara desarrollo con reinicio automático:
npm run devEl 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:stdioPara desarrollo con reinicio automático:
npm run dev:stdioRecursos
El texto estándar incluye estos recursos de ejemplo:
Recurso de información estática :
info://serverProporciona información básica sobre el servidor.
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:
Calculadora : Realiza operaciones aritméticas básicas
Parámetros:
operation: Operación a realizar (sumar, restar, multiplicar, dividir)a: Primer númerob: Segundo número
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:
Saludo : crea un mensaje de saludo personalizado
Parámetros:
name: Nombre para saludarformal: si se debe utilizar el estilo de saludo formal (opcional)
Analizar datos : crea una solicitud para el análisis de datos
Parámetros:
data: Los datos a analizarformat: Formato de datos (json, csv, texto)instructions: Instrucciones de análisis adicionales (opcional)
Ampliación del servidor
Añadiendo recursos
Para agregar un nuevo recurso:
Crea un nuevo archivo en
src/resources/(por ejemplo,myResource.ts)Implemente su controlador de recursos
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:
Crea un nuevo archivo en
src/tools/(por ejemplo,myTool.ts)Implemente su controlador de herramientas
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:
Crea un nuevo archivo en
src/prompts/(por ejemplo,myPrompt.ts)Implemente su controlador de indicaciones
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 toolscalculateD
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | ||
| a | Yes | ||
| b | Yes |
TDQS
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.
timestampD
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | iso |
TDQS
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.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
- First observed
calculate - First observed
timestamp
TDQS
Scored across 2 tools
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.
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.
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.
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
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn educational implementation of a Model Context Protocol server that demonstrates how to build a functional MCP server integrating with various LLM clients.2MIT
- FlicenseBqualityDmaintenanceA 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-
- FlicenseNot gradedqualityDmaintenanceA 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.-
- FlicenseNot gradedqualityDmaintenanceA 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.-