Skip to main content
Glama
enesjakozh
Demontie

Products API MCP Server

by Demontie
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Mi primer proyecto MCP

Este proyecto demuestra el uso del servidor MCP (Protocolo de Contexto de Modelo) que recupera datos de la API DummyJSON . Desarrollado con Cursor IDE y el agente predeterminado.

Tabla de contenido

Related MCP server: openfoodfacts-mcp-server

Características

Herramientas API de productos

  • obtener_productos

    • Descripción: Obtenga una lista de productos con filtrado y paginación opcionales.

    • Parámetros:

      • id (cadena, opcional): Filtrar productos por ID

      • q (cadena, opcional): Filtrar productos por título

      • category (cadena, opcional): Filtrar productos por categoría

      • brand (cadena, opcional): Filtrar productos por marca

      • price (número, opcional): Filtrar productos por precio

      • rating (número, opcional): Filtrar productos por calificación

      • skip (número, opcional, predeterminado: 0): Número de productos a omitir

      • limit (número, opcional, predeterminado: 10): Número máximo de productos a devolver

    • Devoluciones: Una lista de productos que coinciden con los criterios especificados

    • Fuente de datos: API DummyJSON ( https://dummyjson.com/products )

Instalación y uso

Prerrequisitos

  • Node.js (versión 23 o superior)

  • Docker y Docker Compose

  • WSL2 (si usa Windows)

Configuración del cursor

Para configurar este servidor MCP con Cursor:

  1. Cursor abierto

  2. Prensa:

    • Windows/Linux: Ctrl + Shift + P

    • macOS: Cmd + Shift + P

  3. Escriba "Configurar servidor MCP" y selecciónelo

  4. Agregue la configuración adecuada según su configuración:

Para Windows (sin WSL) o Linux:

{
  "mcpServers": {
    "postgres": {
      "command": "node",
      "args": ["ABSOLUTE_PATH_TO_PROJECT/src/index.ts"]
    }
  }
}

Para usuarios de WSL:

{
  "mcpServers": {
    "postgres": {
      "command": "wsl.exe",
      "args": [
        "-e",
        "ABSOLUTE_PATH_TO_NODE/.nvm/versions/node/v23.11.0/bin/node",
        "ABSOLUTE_PATH_TO_PROJECT/src/index.ts"
      ]
    }
  }
}

Para encontrar su ruta Node.js, ejecute:

which node

Licencia

Este proyecto está licenciado bajo la licencia MIT.

Available Tools

1 tool
get_productsC

Get a list of products with optional filtering and pagination.

ParametersJSON Schema
NameRequiredDescriptionDefault
idNoFilter products by ID
qNoFilter products by title
categoryNoFilter products by category
brandNoFilter products by brand
priceNoFilter products by price
ratingNoFilter products by rating
skipNoNumber of products to skip
limitNoMaximum number of products to return

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'optional filtering and pagination,' which hints at read-only behavior and some constraints, but it doesn't detail important aspects like rate limits, authentication needs, error handling, or the format of returned data. For a tool with 8 parameters and no annotations, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that clearly states the tool's purpose and key features (filtering and pagination). It is front-loaded with the main action and avoids unnecessary details, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of 8 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the tool returns, how results are structured, or any behavioral traits beyond basic functionality. For a tool with this level of detail in the schema but lacking output information, more context is needed to be complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, meaning all parameters are well-documented in the input schema. The description adds minimal value beyond this by mentioning 'optional filtering and pagination,' which loosely corresponds to parameters like skip and limit, but it doesn't provide additional semantic context or examples. This meets the baseline score of 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get a list of products' specifies the verb (get) and resource (products). It also mentions optional filtering and pagination, which adds useful context. However, since there are no sibling tools, it doesn't need to differentiate from alternatives, so it doesn't reach the highest score of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives or any specific contexts for usage. It mentions optional filtering and pagination, but this is more about functionality than usage scenarios. Without any explicit when/when-not instructions or prerequisites, it falls short of higher scores.

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. 1 tool update
    • First observedget_products
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose of retrieving products with filtering and pagination capabilities.

Naming Consistency5/5

The single tool name 'get_products' follows a consistent verb_noun pattern, and with only one tool, there is no inconsistency to evaluate. The naming is straightforward and predictable.

Tool Count2/5

A server named 'Products API MCP Server' suggests a domain requiring CRUD operations, but it only provides a single 'get' tool. This is too few for the apparent scope, as it lacks create, update, delete, or other product-related operations, making it severely under-scoped.

Completeness1/5

The tool set is severely incomplete for a products API domain. It only supports retrieving products, with no coverage for creating, updating, deleting, or managing other aspects like categories or inventory. This will cause significant agent failures in typical product management workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • InventarioDB

    diegogfhjk
    F
    license
    Not graded
    quality
    D
    maintenance
    A small MCP server that manages a product inventory using SQLite, providing CRUD operations through exposed MCP tools.
    -

  • jsonplaceholder-mcp

    chatre7
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that provides tools to interact with the JSONPlaceholder fake REST API for testing and prototyping, supporting CRUD operations on posts, comments, todos, and users.
    7
    87 npm
    MIT

Appeared in Searches