bus-scheduling-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_BASE_URL | No | Base URL of the Bus Scheduling Backend API, including /api path. | http://localhost:8000/api |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scheduling_get_kpiA | Fetch key performance indicators (KPIs) like vehicle status, total departures, punctuality rate. |
| scheduling_get_trendsB | Get passenger flow trends for recent dates. |
| scheduling_list_routesA | List all active bus routes with optional filtering by dataset or company. |
| scheduling_get_route_detailsA | Get details of a specific route including stations and departures by route ID. |
| scheduling_list_plansA | List all algorithmically generated scheduling plans. |
| scheduling_get_gantt_dataB | Get plan tasks formatted as Gantt chart data by dataset or plan ID. |
| scheduling_get_optimization_algorithmsA | List available scheduling optimization algorithms (e.g., circular timetable, shift sequence). |
| scheduling_run_optimizationB | Trigger an optimization task with a specific algo_id and parameters. Returns a task ID. |
| scheduling_get_optimization_statusA | Get the status (running, completed, failed) of a specific optimization task by its task ID. |
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 9 tools
Each tool targets a distinct resource and action: routes, route details, Gantt data, optimization algorithms, running/status of optimizations, KPIs, trends, and plans. There is no overlap or ambiguity between them.
All tools follow a consistent scheduling_<verb>_<noun> pattern using only snake_case. Verbs are limited to list, get, and run, making the naming predictable and coherent.
9 tools is well within the ideal 3-15 range and each tool serves a clear purpose in the bus scheduling domain. The count is neither sparse nor overwhelming.
The tool set covers route viewing, optimization execution and status, KPIs, trends, and plan listing. However, there is no direct way to fetch the result of a specific optimization task (only status), nor a get_plan_details tool; the Gantt data requires a plan ID, which may not be known until after listing plans.