TinyTasks MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TinyTasks MCP Server show me my pending tasks and their statistics"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🤖 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.appMCP 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/cliCrear nuevo proyecto:
railway login
railway init
railway upConfigurar variables:
railway variables set WEB_MODE=trueObtener URL:
railway statusOpción 2: Desplegar en Vercel
Instalar Vercel CLI:
npm i -g vercelDesplegar:
vercel --prodUsar en Claude Web
Una vez desplegado, tendrás una URL como:
Railway:
https://tu-proyecto.railway.appVercel:
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.jsModo Claude Web:
WEB_MODE=true node index.jsLuego 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/toolsEjecutar 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
Available Tools
8 toolscreate_taskC
Crea una nueva tarea
Inputs: title (required), detail, priority.
delete_taskC
Elimina permanentemente una tarea
Inputs: id (required).
get_api_statusB
Obtiene el estado actual de la API de TinyTasks
Inputs: no named parameters.
get_taskC
Obtiene los detalles de una tarea específica
Inputs: id (required).
get_tasks_statsB
Obtiene estadísticas de las tareas: total, completadas, pendientes
Inputs: no named parameters.
list_tasksC
Lista todas las tareas con filtro opcional por estado
Inputs: status.
toggle_taskC
Alterna el estado de completación de una tarea
Inputs: id (required).
update_taskC
Actualiza una tarea existente
Inputs: id (required), title, detail, priority, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clearly distinct purpose with no overlap: create, delete, get, list, update, toggle, and API status/statistics tools all target specific actions on tasks or system status. An agent can easily differentiate between them based on their descriptions.
All tools follow a consistent verb_noun naming pattern (e.g., create_task, delete_task, get_task) with clear, descriptive verbs. There are no deviations in style or convention across the set.
With 8 tools, this server is well-scoped for task management, covering core CRUD operations (create, get, update, delete), listing, toggling completion, and supplementary functions like stats and API status. Each tool earns its place without bloat.
The toolset provides complete coverage for task management: full CRUD (create, get, update, delete), lifecycle handling (toggle for completion), listing with filters, statistics, and system status. There are no obvious gaps that would hinder an agent's workflow.
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
ADHD-friendly task management MCP server for ChaTodo: organize tasks, lists, and priorities.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Official Todoist MCP server. Manage tasks and projects. Hosted, no API key needed.