Koleo MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KOLEO_MCP_CONFIG | No | Optional path to the config.json file (defaults to ~/.config/koleo-mcp/config.json). The config file can contain 'email' and 'password' for authentication. |
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 |
|---|---|
| tool_search_stationsB | Search for train stations by name. Returns station IDs, slugs, and types. |
| tool_get_station_infoA | Get detailed info about a station: address, opening hours, available facilities. |
| tool_get_departuresC | Get upcoming train departures from a station. |
| tool_get_arrivalsC | Get upcoming train arrivals at a station. |
| tool_get_all_trainsA | Get all trains (both departures and arrivals) at a station, sorted by time. |
| tool_search_connectionsC | Search for train connections between two stations. |
| tool_get_train_routeC | Get the full route and stop schedule for a train by brand and number. |
| tool_get_train_by_idB | Get a train's route and stops by its internal Koleo ID. |
| tool_get_train_calendarC | Get all dates when a specific train runs (operating calendar). |
| tool_get_seat_statsC | Check seat occupancy statistics for a train on a given route segment. |
| tool_get_seat_availabilityC | Get raw seat availability for a connection by connection_id, train_nr, and place_type. |
| tool_get_brandsB | List all available train brands/operators (IC, REG, EIC, KM, etc.). |
| tool_get_carriersB | List all train carriers (PKP Intercity, POLREGIO, etc.). |
| tool_get_realtime_timetableB | Get realtime timetable for a train, including actual vs scheduled times. Requires authentication in config. |
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 14 tools
Every tool has a clearly distinct purpose with no ambiguity. For example, tool_get_arrivals and tool_get_departures are clearly separated by direction, while tool_get_train_by_id and tool_get_train_route target different lookup methods. The descriptions reinforce these distinctions, making misselection unlikely.
All tool names follow a consistent verb_noun pattern with 'tool_get_' or 'tool_search_' prefixes, followed by descriptive nouns. This uniformity (e.g., tool_get_all_trains, tool_search_connections) makes the set predictable and easy to navigate, with no deviations in style.
With 14 tools, the count is well-scoped for a train information server, covering core operations like station lookups, train schedules, seat availability, and connections. Each tool earns its place without feeling bloated or insufficient for the domain.
The tool surface provides complete coverage for train-related queries, including CRUD-like operations (e.g., get, search), real-time data, seat information, and station details. There are no obvious gaps; agents can handle typical workflows from planning to real-time updates without dead ends.