RTIdeas MCP API Server
Converts a local MCP server into a remote HTTP-accessible REST API server with MongoDB support for managing brainstorming sessions and ideas. Provides endpoints for listing sessions, searching ideas, analyzing connections, and generating statistics.
README
RTIdeas MCP API Server
Servidor API REST para RTIdeas con soporte MongoDB. Convierte tu MCP local en un servidor remoto accesible vía HTTP.
🚀 Inicio Rápido
1. Instalar Dependencias
pip install -r requirements.txt
2. Configurar Variables de Entorno
cp env.example .env
# Editar .env con tu MONGODB_URI
3. Iniciar Servidor
# Desarrollo (con auto-reload)
python dev_server.py
# Producción
python server.py
📁 Archivos Principales
server.py- Archivo principal del servidor (para producción)dev_server.py- Servidor de desarrollo (con auto-reload)rtideas_api_server.py- Lógica principal del servidor APIconfig.py- Configuración del servidormongodb_connector.py- Conector a MongoDBrequirements.txt- Dependencias Pythonenv.example- Variables de entorno de ejemplo
🌐 URLs del Servidor
- API: http://localhost:8000
- Documentación: http://localhost:8000/docs
- Health Check: http://localhost:8000/health
📡 Endpoints Disponibles
Herramientas MCP (POST)
POST /tools/list_sessions
POST /tools/get_session
POST /tools/list_ideas
POST /tools/search_ideas
POST /tools/get_idea_connections
POST /tools/get_idea_clusters
POST /tools/get_session_stats
POST /tools/analyze_session
POST /tools/hello_rtideas
Recursos MCP (GET)
GET /resources/sessions
GET /resources/ideas/{session_id}
GET /resources/connections/{session_id}
GET /resources/clusters/{session_id}
GET /resources/stats/{session_id}
🚀 Despliegue en Servidor
Opción 1: Docker (Recomendado)
# Crear docker-compose.yml
docker-compose up -d
Opción 2: VPS/Cloud
# Instalar dependencias
pip install -r requirements.txt
# Configurar variables de entorno
cp env.example .env
nano .env
# Iniciar servidor
python server.py
Opción 3: Con Gunicorn (Producción)
gunicorn rtideas_api_server:app -w 4 -k uvicorn.workers.UvicornWorker --bind 0.0.0.0:8000
🔧 Variables de Entorno
| Variable | Descripción | Valor por Defecto |
|---|---|---|
MONGODB_URI |
URI de conexión MongoDB | Requerido |
MONGODB_DATABASE |
Nombre de la base de datos | rtideas |
API_HOST |
Host del servidor | 0.0.0.0 |
API_PORT |
Puerto del servidor | 8000 |
API_RELOAD |
Auto-reload en desarrollo | false |
CORS_ORIGINS |
Orígenes permitidos | * |
📊 Ejemplo de Uso
# Health check
curl http://localhost:8000/health
# Listar herramientas
curl http://localhost:8000/tools
# Usar herramienta
curl -X POST "http://localhost:8000/tools/hello_rtideas" \
-H "Content-Type: application/json" \
-d '{"name": "Usuario"}'
🔒 Seguridad
- Configurar
CORS_ORIGINSen producción - Usar HTTPS en producción
- Agregar autenticación si es necesario
📝 Logs y Monitoreo
# Ver logs del servidor
tail -f server.log
# Health check
curl http://localhost:8000/health
🆘 Troubleshooting
- Puerto en uso: Cambiar
API_PORTen.env - MongoDB no conecta: Verificar
MONGODB_URI - CORS errors: Configurar
CORS_ORIGINS
Para más detalles, ver DEPLOYMENT.md.
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.
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.
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.
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.