RedTransporteMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RED_TRANSPORTE_API_URL | No | Base URL of the API REST | https://api-red.iroak.dev |
| RED_TRANSPORTE_MCP_PORT | No | Port of the HTTP transport | 8001 |
| RED_TRANSPORTE_API_TOKEN | Yes | Bearer token for the API (create in POST /admin/tokens) | |
| RED_TRANSPORTE_MCP_TOKEN | No | Bearer token required for the MCP client (required for HTTP transport) | |
| RED_TRANSPORTE_MCP_TIMEOUT | No | Timeout for API calls to the REST server (seconds) | 30 |
| RED_TRANSPORTE_MCP_BASE_URL | No | Canonical URL of the OAuth resource; the final resource is /mcp | https://mcp-red.iroak.dev |
| RED_TRANSPORTE_OAUTH_SECRET | No | Optional separate HMAC secret for OAuth clients and tokens | |
| RED_TRANSPORTE_MCP_PUBLIC_HOST | No | HTTP hostname allowed by the DNS-rebinding protection | mcp-red.iroak.dev |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_stopsA | Buscar paraderos de Santiago por nombre o código parcial. Útil cuando el usuario menciona un lugar o intersección y hay que resolver el código del paradero. |
| get_stopB | Obtener información detallada de un paradero por su código: nombre, coordenadas, accesibilidad y servicios que pasan por él. |
| find_nearby_stopsB | Encontrar paraderos dentro de un radio (km) de una coordenada, ordenados por distancia. |
| find_closest_stationA | Encontrar la estación de metro o tren más cercana a una coordenada, con sus servicios. |
| get_routes_near_pointB | Recorridos que pasan cerca de una coordenada, dentro de un radio. |
| find_stops_in_bboxB | Paraderos dentro de un bounding box (min/max lat/lon). |
| list_routesB | Listar recorridos, opcionalmente filtrados por modo (bus, metro, rail, tram). |
| get_routeA | Detalle de un recorrido: nombre, color, modo, paradas de ida/vuelta y frecuencias por día. |
| get_route_stopsB | Secuencia de paradas de un recorrido en una dirección (0=ida, 1=vuelta). |
| get_route_shapeB | Geometría (shape) de un recorrido como coordenadas [lon, lat]. |
| get_arrivalsB | Predicciones de llegada en tiempo real para un paradero (iBus + RED web). Usar después de resolver el código con search_stops. |
| suggest_direct_routesA | Sugerir recorridos directos que conecten dos puntos. No planifica transbordos; para eso usar plan_journey. |
| plan_journeyA | Planificar un viaje en transporte público entre dos coordenadas (RAPTOR): alternativas con transbordos, tiempos y tarifa integrada. day: L=laboral, S=sábado, D=domingo. fare_type: normal, estudiante, adulto_mayor. |
| get_system_statsB | Estadísticas del dataset GTFS: paraderos, recorridos, viajes, modos. |
| get_gtfs_statusB | Estado del dataset GTFS: disponible, fecha de descarga, vigencia. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 15 tools
Tools are mostly distinct with clear purposes: stop lookup (search_stops/get_stop/find_nearby_stops), route lookup (list_routes/get_route/get_route_stops/get_route_shape), and journey planning (plan_journey/suggest_direct_routes). Some minor boundary overlap exists between route stop listing (get_route_stops, get_route) and spatial queries (find_nearby_stops, find_closest_station, get_routes_near_point, find_stops_in_bbox), which could cause some ambiguity but descriptions help disambiguate them.
Names mostly follow a consistent get_/find_/list_/search_/suggest_/plan_ prefix pattern with descriptive object suffixes. Minor inconsistencies: mix of get_/find_/list_ for data retrieval operations is permissible but not perfectly uniform, and get_system_stats vs get_gtfs_status are somewhat similar in style. Overall predictable and readable.
15 tools is on the higher end but appropriate for a comprehensive transit MCP server covering stops, routes, journey planning, arrival predictions, and dataset health. Each tool appears to earn its place covering distinct data needs.
The surface is comprehensive: spatial queries (nearby, bbox), route listing/detail/geometry, stop search/detail, arrivals, journey planning with mode and fare options, plus GTFS dataset status. Minor gaps exist, such as direct route-to-route stop exploration without coordinates (though get_route covers this), and no route filtering by arrival time, but the core transit workflows are well covered.