TinyTasks MCP Server
A hybrid MCP server that allows users to manage tasks through Claude Desktop or Claude Web using a NestJS API. It provides eight tools for creating, updating, listing, and tracking statistics for personal tasks.
README
🤖 TinyTasks MCP Server
Servidor MCP híbrido que funciona tanto con Claude Desktop como con Claude Web.
✅ Estado del Proyecto
- API NestJS: ✅ Funcionando en
https://forgetful-production-a037.up.railway.app - MCP Server Local: ✅ Listo para Claude Desktop
- MCP Server Web: ✅ Listo para despliegue y Claude Web
- 8 Herramientas: ✅ Todas implementadas y probadas
🛠️ Herramientas Disponibles
- get_api_status - Estado de la API
- get_tasks_stats - Estadísticas de tareas
- list_tasks - Listar tareas (con filtros)
- get_task - Obtener tarea específica
- create_task - Crear nueva tarea
- update_task - Actualizar tarea
- toggle_task - Alternar estado
- delete_task - Eliminar tarea
🌐 Para Claude Web (Servidor Público)
Opción 1: Desplegar en Railway
- Instalar Railway CLI:
npm i -g @railway/cli
- Crear nuevo proyecto:
railway login
railway init
railway up
- Configurar variables:
railway variables set WEB_MODE=true
- Obtener URL:
railway status
Opción 2: Desplegar en Vercel
- Instalar Vercel CLI:
npm i -g vercel
- Desplegar:
vercel --prod
Usar en Claude Web
Una vez desplegado, tendrás una URL como:
- Railway:
https://tu-proyecto.railway.app - Vercel:
https://tu-proyecto.vercel.app
Endpoints disponibles:
GET /- Información del servidorGET /mcp/tools- Lista de herramientasPOST /mcp/execute- Ejecutar herramienta
Ejemplo de uso en Claude Web:
Puedes usar mi MCP server en: https://tu-proyecto.railway.app
Herramientas disponibles en: https://tu-proyecto.railway.app/mcp/tools
Para ejecutar una herramienta, haz POST a: https://tu-proyecto.railway.app/mcp/execute
con el body: {"tool": "get_tasks_stats"}
🖥️ Para Claude Desktop (Servidor Local)
1. Configurar Claude Desktop
Edita: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"tinytasks": {
"command": "node",
"args": ["/Users/franciscogoulu/Desktop/Fran Dev/Forgetful3/mcp-tinytasks-server/index.js"],
"env": {
"NODE_ENV": "production"
}
}
}
}
2. Reiniciar Claude Desktop
🧪 Probar Localmente
Modo Claude Desktop:
node index.js
Modo Claude Web:
WEB_MODE=true node index.js
Luego visita: http://localhost:3001
📋 Endpoints de la API Web
GET /
Información del servidor
GET /mcp/tools
Lista todas las herramientas disponibles
POST /mcp/execute
Ejecuta una herramienta específica
Body:
{
"tool": "get_tasks_stats",
"arguments": {}
}
Ejemplo con argumentos:
{
"tool": "create_task",
"arguments": {
"title": "Nueva tarea desde Claude Web",
"priority": "high"
}
}
🔍 Verificar Funcionamiento
Probar API directamente:
curl https://tu-mcp-server.railway.app/mcp/tools
Ejecutar herramienta:
curl -X POST https://tu-mcp-server.railway.app/mcp/execute \
-H "Content-Type: application/json" \
-d '{"tool": "get_api_status"}'
🎯 Resumen de Opciones
Para Claude Desktop:
- Usa el servidor local con protocolo MCP nativo
- Configuración en
claude_desktop_config.json
Para Claude Web:
- Despliega el servidor como API REST
- Usa endpoints HTTP para comunicación
- Accesible desde cualquier lugar
¡Ambos modos consumen la misma API de TinyTasks! # Updated Sun Jun 15 20:54:37 -03 2025
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.