Skip to main content
Glama
enesjakozh
ChenReuven

MCP TypeScript Simple Template

by ChenReuven
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

Plantilla simple de TypeScript de MCP

Una plantilla sencilla de TypeScript para crear servidores de Protocolo de Contexto de Modelo (MCP). Este proyecto proporciona una base para crear herramientas MCP personalizadas que se pueden integrar con sistemas de IA.

Descripción general

Esta plantilla implementa un servidor MCP básico con una herramienta de cálculo de IMC de ejemplo. Demuestra cómo:

  • Configurar un servidor MCP en TypeScript

  • Definir e implementar herramientas MCP con validación de entrada utilizando Zod

  • Conecte el servidor a la E/S estándar para la comunicación

Related MCP server: MCP Server Python Template

Prerrequisitos

  • Node.js (se recomienda v20 o superior)

  • npm o hilo

Instalación

  1. Clonar este repositorio

  2. Instalar dependencias:

npm install

Estructura del proyecto

  • index.ts - Implementación del servidor principal con herramienta de ejemplo

  • package.json - Dependencias y scripts del proyecto

  • tsconfig.json - Configuración de TypeScript

Uso

Construyendo y funcionando

Construya e inicie el servidor:

npm start

Esto compilará el código TypeScript e iniciará el servidor MCP.

Desarrollo

Para el desarrollo, puedes:

  1. Modifique index.ts para agregar sus propias herramientas

  2. Ejecute el comando de compilación para compilar:

npm run build

Creación de herramientas personalizadas

Para crear una nueva herramienta, siga este patrón en index.ts :

server.tool(
  "your-tool-name",
  {
    // Define input schema using Zod
    paramName: z.string(),
    // Add more parameters as needed
  },
  async ({ paramName }) => ({
    content: [{
      type: "text",
      text: "Your tool's response"
    }]
  })
);

Dependencias

  • @modelcontextprotocol/sdk - SDK principal de MCP

  • zod - Validación de esquemas

  • dotenv - Gestión de variables de entorno

  • typescript - compilador de TypeScript

Licencia

ISC

Contribuyendo

¡Agradecemos sus contribuciones! No dude en enviar una solicitud de incorporación de cambios.

Available Tools

2 tools
calculate-bmiD
ParametersJSON Schema
NameRequiredDescriptionDefault
heightMYes
weightKgYes

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.

echoD
ParametersJSON Schema
NameRequiredDescriptionDefault
textYes

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 updatesv1.0.0
    • First observedcalculate-bmi
    • First observedecho
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

D1.5/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: calculate_bmi is for health-related calculations, while echo is for text repetition. There is no overlap or ambiguity between them, making it easy for an agent to choose the right tool.

Naming Consistency2/5

The naming is inconsistent: calculate_bmi uses kebab-case, while echo uses lowercase without a clear pattern. There is no consistent verb_noun convention, and the styles are mixed, though the names are still readable.

Tool Count2/5

With only 2 tools, the server feels too thin for a general-purpose template. It lacks depth and variety, suggesting an incomplete or minimal implementation that doesn't fully cover a meaningful domain.

Completeness1/5

The server is severely incomplete; it only offers two unrelated tools with no descriptions, making it impossible to assess domain coverage. There are obvious gaps, and it doesn't support any coherent workflow or lifecycle.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Server Python Template

    Cris-0k
    A
    license
    Not graded
    quality
    Not graded
    maintenance
    A streamlined foundation for building Model Context Protocol servers in Python, designed to make AI-assisted development of MCP tools easier and more efficient.
    12
    MIT

  • MCP Starter

    instructa
    A
    license
    D
    quality
    D
    maintenance
    A foundation for building custom local Model Context Protocol (MCP) servers that provide tools accessible to AI assistants like Cursor or Claude Desktop.
    1
    37
    MIT

  • Python MCP Server Template

    HappyPathway
    -
    license
    Not graded
    quality
    D
    maintenance
    A standardized foundation for building Model Context Protocol servers that integrate with VS Code, using Python with stdio transport for seamless AI tool integration.
    -

Appeared in Searches