parking-recommendation
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEOUL_API_KEY | No | Seoul Open API key for parking lot data. If not set, mock data is used. | |
| KAKAO_REST_API_KEY | No | Kakao REST API key for destination search. If not set, mock data is used. | |
| SEOUL_PARKING_ENDPOINT | No | Seoul Open API endpoint for parking lot data. | http://openapi.seoul.go.kr:8088 |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_destinationA | 사용자가 입력한 목적지명을 좌표로 변환합니다. |
| find_parking_lotsB | 목적지명 또는 좌표 기준으로 주변 주차장을 찾습니다. 답변에는 availability_summary(예: 🟢 여유 · 42/120면 가능), distance_summary(예: 450m · 도보 7분), 카카오맵 링크를 함께 보여주세요. |
| get_parking_detailA | 주차장의 상세 정보, 가능대수, 운영시간, 요금 정보를 조회합니다. |
| estimate_wait_timeB | 실시간 가능대수와 과거 출차 통계를 바탕으로 예상 대기시간을 계산합니다. |
| recommend_parkingB | 목적지 주변 주차장을 거리, 대기시간, 요금, 초보 친화도 기준으로 추천합니다. 답변에는 각 추천의 availability_summary(예: 🟢 여유 · 42/120면 가능), distance_summary(예: 450m · 도보 7분), 예상 대기시간, 카카오맵 링크를 함께 보여주세요. |
| analyze_parking_congestionB | 평일/주말 기준으로 혼잡하거나 대기 가능성이 높은 주차장을 분석합니다. 결과의 availability_summary, distance_summary, congestion_score를 답변에 함께 보여주세요. |
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 6 tools
Most tools have clearly distinct roles: geocoding, listing, detail, wait-time, recommendation, and congestion analysis. However, find_parking_lots, recommend_parking, and analyze_parking_congestion all return overlapping availability/distance summaries, which could cause some selection ambiguity.
All tool names follow a consistent verb_noun pattern with clear action prefixes: search, find, get, estimate, recommend, analyze. No mixed conventions or vague verbs.
Six tools cover the parking recommendation workflow without redundancy or bloat. Each tool addresses a distinct stage or type of query an agent would need.
The toolset forms a complete workflow: geocode destination, find parking lots, inspect details, estimate wait time, get recommendations, and analyze congestion. No critical dead ends or missing operations for the stated purpose.