obilet-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| obilet_search_locationsA | Search obilet.com locations (cities, towns, airports) by name. query: e.g. "Ankara", "İstanbul", "İzmir". kind: "bus" (default, int ids) or "flight" (string ids like "250_0"). Returns id, name, display name and city id per match. Use the id in obilet_search_bus_journeys (bus) or obilet_flight_summary (flight). |
| obilet_search_bus_journeysA | Bus journeys for one route + date. origin_id / destination_id: bus location ids from obilet_search_locations (e.g. İstanbul Avrupa 349 -> Ankara 356). date: YYYY-MM-DD (e.g. "2026-11-07"). sort: "price_asc" (cheapest first, default), "departure" (earliest first), "duration" (shortest first). limit 1..24. Returns journey id, partner, bus type, seats, origin/destination stations, departure/arrival, duration, price in TRY, partner rating (0-10) and stops per journey, plus the total count for the route. |
| obilet_journey_detailA | Full detail of one bus journey: partner, bus type, seats, origin/destination stations, departure/arrival, duration, internet price and original price in TRY, service fee, partner rating, bus name, platform (peron), description and every stop with its time. journey_id: from obilet_search_bus_journeys. |
| obilet_price_statsB | Price statistics for a bus route + date: journey count, min / median / mean / max ticket price in TRY across all journeys. origin_id / destination_id: bus location ids; date: YYYY-MM-DD. |
| obilet_flight_summaryA | Flight summary for a route + date (from the bus-journeys response): flight count, min/max price in TRY, min/max duration, first/last departure, direct-flight flag and airlines with IATA codes. origin_id / destination_id: bus location ids (the summary covers the same city pair); date: YYYY-MM-DD. Note: individual flight listings are NOT available in v1 (the async flights endpoint is broken on the site side). |
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 5 tools
Each tool has a recognizable role: location lookup, bus journey search, journey detail, aggregate price stats, and flight summary. The main soft overlap is between obilet_price_stats and obilet_search_bus_journeys, since both take route+date and prices already appear in journey results, and price_stats is bus-only while flight_summary also reports price ranges. Descriptions do clarify the distinction (aggregate vs. listings), so confusion is limited.
All five tools share the obilet_ prefix and snake_case, which makes the set predictable and easy to scan. The only inconsistency is verb style: search_locations and search_bus_journeys lead with a verb, while price_stats, journey_detail, and flight_summary are noun-first phrases. It is still readable but not a strict verb_noun pattern.
Five tools is well within a healthy range for a read-only travel search domain. Each tool covers a distinct step (resolve locations, list journeys, inspect a journey, aggregate prices, summarize flights) with no filler tools. Nothing feels padded or conspicuously missing at the count level.
The surface supports the core workflow: find location ids, search bus journeys, drill into a journey, get price statistics, and get a flight overview. Gaps exist but are documented—no individual flight listings (explicitly broken upstream in v1) and no booking/purchase or advanced filtering on bus results. Agents can work around these within the stated informational purpose.