A
licenseNot graded
qualityD
maintenanceA Model Context Protocol server built with mcp-framework that allows users to create and manage custom tools for processing data, integrating with the Claude Desktop via CLI.
32 npm
5
MIT
Hello-MCP
by hongsw
🚀 Hola MCP (Protocolo de Contexto de Modelo)
Herramienta de guía para configurar el administrador de configuración MCP de Claude Desktop
한국어 버전은 아래 링크에서 확인할 수 있습니다. 한국어 버전
La versión en inglés está disponible en el siguiente enlace. Versión en inglés
✨ Descripción general
Hello-MCP es una herramienta útil que permite a Claude Desktop interactuar con herramientas externas mediante el Protocolo de Contexto de Modelo (MCP). Simplifica el proceso de configuración y proporciona una integración perfecta entre Claude AI y sus herramientas personalizadas.
(inglés) ¡Hola, bienvenido! (coreano) 안녕하세요, 환영합니다!
Related MCP server: my-mcp-server
🛠️ Características
Configuración sencilla : configuración sencilla con un solo comando para la integración de Claude Desktop MCP
Modos múltiples : ejecutar como asistente de configuración, servidor MCP o herramienta CLI
Herramientas de muestra integradas : herramientas preconfiguradas como envío de correo electrónico y cálculos sencillos
Extensible : agregue fácilmente sus propias herramientas MCP
Internacionalización : admite varios idiomas (coreano e inglés)
📋 Requisitos
Descargar Node.js 14+
Claude Desktop instalado ( Descargar aquí )
Conexión a Internet para el envío de correo electrónico Generación de claves API de GARAK
🚀 Inicio rápido
Puede ejecutar Hello-MCP sin instalación usando npx:
npx hello-mcpEsto iniciará el asistente de configuración que lo guiará a través de todo el proceso de configuración.
🎮 Uso
Hi-Garak se puede utilizar en tres modos diferentes:
1️⃣ Modo de configuración (predeterminado)
npx hello-mcp
# or
npx hello-mcp setupEste modo interactivo permitirá:
Comprueba si Claude Desktop está instalado
Pide tu email y propósito
Generar una clave API
Configurar Claude Desktop para MCP
Reiniciar Claude Desktop automáticamente (cuando sea posible)
2️⃣ Modo servidor MCP
npx hello-mcp mcp-serverEsto inicia Hello-MCP como un servidor MCP al que Claude Desktop puede conectarse. El servidor proporciona herramientas que Claude puede usar para realizar acciones.
🔑 Claves API
Su clave API se almacena en ~/.garakrc y tiene un límite diario de 50 solicitudes. La clave se configura automáticamente para su uso con Claude Desktop.
📊 Telemetría
Hello-MCP recopila datos de uso anónimos para mejorar el servicio:
Interacciones del usuario y métricas de rendimiento
Todos los datos están anonimizados.
Puede desactivar la telemetría en la configuración
🌟 Consejos para usar con Claude
Después de la configuración, puedes probar estas indicaciones con Claude:
"1 suma 1" (Cálculo simple)
"Envía un correo electrónico a [tu-correo] con el resultado de 1 suma 1"
🤝 Apoyo
Si tiene algún problema, contáctenos en help@garak.ai
📚 Documentación
Para obtener más ejemplos y sugerencias, visite nuestra guía de inicio: Guía de inicio
También puedes navegar por nuestra documentación interactiva:
Ejecutar localmente:
npx docsify-cli serve docsVer en su navegador: http://localhost:3000
🚧 TODO
Si encuentra algún problema o tiene alguna sugerencia, cree un problema en un sistema de seguimiento de problemas adecuado (por ejemplo, GitHub Issues). Proporcione una descripción detallada del problema y los pasos para reproducirlo. https://github.com/hongsw/hello-mcp/issues
La compatibilidad con Windows se encuentra actualmente en pruebas.
📄 Licencia
Este proyecto está licenciado bajo la licencia MIT: consulte el archivo de LICENCIA para obtener más detalles.
Available Tools
2 toolsaddD
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | ||
| b | Yes |
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.
send-emailD
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | |||
| body | Yes |
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.
2 tool updates
v1.0.0- First observed
add - First observed
send-email
TDQS
D1.2/5.0
Scored across 2 tools
Disambiguation2/5
The two tools, 'add' and 'send-email', have no descriptions and appear to serve completely unrelated purposes. An agent cannot determine what 'add' refers to or how it relates to sending email, creating ambiguity.
Naming Consistency2/5
The tool names follow no consistent pattern: 'add' is a bare verb while 'send-email' uses a verb-noun format with a hyphen. The lack of a shared convention makes the set feel ad hoc.
Tool Count2/5
With only two tools and no descriptions, the server appears extremely thin and under-scoped. It is unclear what domain it covers, and two unrelated tools do not form a coherent toolkit.
Completeness1/5
The server's purpose is entirely unclear from the tool names alone. 'add' and 'send-email' do not suggest any complete workflow or domain coverage, leaving obvious gaps in any conceivable use case.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
- QuallaaOAuthcom.quallaa
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that allows integration with Claude Desktop by creating and managing custom tools that can be executed through the MCP framework.59 npm-
- AlicenseNot gradedqualityDmaintenanceA tool that helps users easily register Anthropic's Model Context Protocol in Claude Desktop and Cursor, providing ready-made MCP tools for RAG, web search, and Dify integrations.MIT
- AlicenseNot gradedqualityDmaintenanceA local Model Context Protocol (MCP) server that exposes custom tools to Claude Desktop, enabling direct interaction with your local environment. It provides a framework for building and integrating custom TypeScript tools into the Claude interface.1 npmMIT