Skip to main content
Glama
enesjakozh
pinnaclesoft-ko

Seoul Public Data MCP Server

by pinnaclesoft-ko
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

Seoul Public Data MCP Server Example

This is an example of an MCP server that provides various public data of Seoul using the Seoul Public Data API.

List of examples

  • Information on the number of passengers getting on and off at each subway line and station in Seoul

  • Seoul City Cultural Event Information

Related MCP server: k-skill-korea

How to set up

Setting up Seoul Public Data API Key

Information on the number of passengers getting on and off at each subway line and station in Seoul

Add the following {API key} to the file modules/KoreaSeoulCulturalEventInfo.ts .

import {
    Tool,
} from "@modelcontextprotocol/sdk/types.js";

const API_URL = "http://openapi.seoul.go.kr:8088/{authKey}/json/culturalEventInfo/{StartIndex}/{EndIndex}";
const API_KEY = "{API 키}";

Seoul City Cultural Event Information

Add the following {API key} to the file modules/KoreaSeoulSubwayStatus.ts .

import {
    Tool,
} from "@modelcontextprotocol/sdk/types.js";

const API_URL = "http://openapi.seoul.go.kr:8088/{authKey}/json/culturalEventInfo/{StartIndex}/{EndIndex}";
const API_KEY = "{API 키}";

Build it

npm i; npm run build

Adding MCP Settings to Claude Desktop

Add the following to claude_desktop_config.json file. Replace {built path} with your own.

{
  "mcpServers": {
    "KoreaSeoulData": {
      "command": "node",
      "args": [
        "{빌드된 경로}/seoul_korea/dist/index.js"
      ]
    }
  }
}

Usage examples

Information on the number of passengers getting on and off at each subway line and station in Seoul

image

Seoul City Cultural Event Information

image

Available Tools

2 tools
CulturalEventInfoC

서울시 문화행사 정보를 조회할 수 있는 도구입니다.

서울문화포털에서 제공하는 문화행사 정보입니다. 공연, 행사에 대한 장소, 날짜, 기관명, 이용대상, 이용요금, 출연자, 프로그램 등의 정보를 제공합니다.

반환되는 데이터는 JSON 형식으로 제공되며, 반환되는 데이터의 구조는 다음과 같습니다:

list_total_count: 총 데이터 건수
RESULT.CODE: 결과 코드
RESULT.MESSAGE: 결과 메시지
row: 데이터 배열
  
  각 데이터는 다음과 같은 필드를 포함합니다:

  CODENAME: 분류
  GUNAME: 자치구
  TITLE: 공연/행사명
  DATE: 날짜/시간
  PLACE: 장소
  ORG_NAME: 기관명
  USE_TRGT: 이용대상
  USE_FEE: 이용요금
  PLAYER: 출연자정보
  PROGRAM: 프로그램소개
  ETC_DESC: 기타정보
  ORG_LINK: 홈페이지 주소
  MAIN_IMG: 대표이미지
  RGSTDATE: 등록일
  TICKET: 시민/기관
  STRTDATE: 시작일
  END_DATE: 종료일
  THEMECODE: 테마분류
  LOT: 위도
  LAT: 경도
  IS_FREE: 무료여부
  HMPG_ADDR: 문화포털상세URL
ParametersJSON Schema
NameRequiredDescriptionDefault
startIndexYes요청시작위치, 정수 입력 (페이징 시작번호 입니다 : 데이터 행 시작번호), 기본값 1을 사용합니다.
endIndexYes요청종료위치, 정수 입력 (페이징 끝번호 입니다 : 데이터 행 끝번호), 기본값 10을 사용합니다. 최대값은 list_total_count입니다.

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It describes the return data format (JSON) and structure, which is helpful, but lacks critical behavioral details: it doesn't mention rate limits, authentication requirements, error handling, or whether this is a read-only operation (implied by '조회' but not explicit). The description adds some context but misses key operational traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and appropriately sized. It starts with the tool's purpose, details the data source and fields, and explains the return format with a clear breakdown. However, the detailed field listing could be condensed or moved to an output schema for better conciseness, though it's informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (2 parameters, no annotations, no output schema), the description is moderately complete. It covers the purpose, data fields, and return structure, which helps compensate for the lack of output schema. However, it lacks behavioral context (e.g., rate limits, errors) and usage guidelines, leaving gaps for an agent to operate effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, clearly documenting both parameters (startIndex and endIndex) with their purposes, types, and constraints. The description adds no parameter-specific information beyond what's in the schema, so it meets the baseline of 3 for high schema coverage without compensating value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '서울시 문화행사 정보를 조회할 수 있는 도구입니다' (a tool to query cultural event information in Seoul). It specifies the data source (Seoul Culture Portal) and the type of information provided (performances, events with location, date, etc.). However, it doesn't explicitly differentiate from the sibling tool 'KoreaSeoulSubwayStatus', which handles subway status rather than cultural events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions the data source but doesn't specify use cases, prerequisites, or exclusions. There's no comparison with the sibling tool or other potential tools for cultural event queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

KoreaSeoulSubwayStatusB

서울시 지하철호선별 역별 승하차 인원 정보를 조회할 수 있는 도구입니다.

날짜는 YYYYMMDD 형식으로 입력해야 하며, 지하철역 이름은 한글로 입력해야 합니다. 예를 들어, "서울역"은 "서울"과 같은 형식입니다. 지하철 노선 번호는 "1호선", "2호선"과 같은 형식으로 입력해야 합니다.

반환되는 데이터는 JSON 형식으로 제공되며, 반환되는 데이터의 구조는 다음과 같습니다:

list_total_count: 총 데이터 건수
RESULT.CODE: 결과 코드
RESULT.MESSAGE: 결과 메시지
row: 데이터 배열
  
  각 데이터는 다음과 같은 필드를 포함합니다:

  USE_YMD: 사용일자
  SBWY_ROUT_LN_NM: 호선명
  SBWY_STNS_NM: 역명
  GTON_TNOPE: 승차인원
  GTOFF_TNOPE: 하차인원
  REG_YMDT: 등록일자
ParametersJSON Schema
NameRequiredDescriptionDefault
startIndexNo요청시작위치, 정수 입력 (페이징 시작번호 입니다 : 데이터 행 시작번호), 기본값 1을 사용합니다.
endIndexNo요청종료위치, 정수 입력 (페이징 끝번호 입니다 : 데이터 행 끝번호), 기본값 10을 사용합니다.
dateYes사용일자, YYYYMMDD 형식의 문자열.
subwayLineNoYes한국 서울 지하철 호선명. 지하철 호선(공백시 %20으로 조회)
subwayStationNameYes한국 서울 지하철 역명.

TDQS

B3.1/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses the return format (JSON) and data structure details, which is valuable. However, it doesn't mention important behavioral aspects like whether this is a read-only operation (implied but not stated), rate limits, authentication requirements, or error handling beyond the RESULT.CODE/MESSAGE fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized but not optimally structured. It front-loads the purpose, but then mixes parameter format instructions with output structure details. The output structure section is quite detailed (listing 7 specific fields) which might be better suited for an output schema. Some sentences could be more efficiently combined.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters, no annotations, and no output schema, the description provides reasonable coverage. It explains the purpose, parameter formats, and output structure. However, for a data retrieval tool with pagination parameters (startIndex/endIndex), it doesn't explain pagination behavior or how to interpret the list_total_count field in relation to the pagination parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds some value by reinforcing format requirements (YYYYMMDD for date, Korean for station names, specific formats for line numbers) and providing examples, but doesn't add significant semantic meaning beyond what's in the schema descriptions. Baseline 3 is appropriate when schema does most of the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: '서울시 지하철호선별 역별 승하차 인원 정보를 조회할 수 있는 도구입니다' (retrieves subway passenger boarding/alighting information by line and station in Seoul). It specifies the resource (subway passenger data) and verb (조회/retrieve), but doesn't explicitly differentiate from the sibling tool 'CulturalEventInfo' beyond being in a different domain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling tool 'CulturalEventInfo' or any other tools that might exist for similar data queries. Usage context is implied (when you need subway passenger data) but not explicitly stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updates
    • First observedCulturalEventInfo
    • First observedKoreaSeoulSubwayStatus
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3/5.0
Disambiguation5/5

The two tools have completely distinct purposes with no overlap. CulturalEventInfo retrieves cultural event information from Seoul's cultural portal, while KoreaSeoulSubwayStatus provides subway station passenger count data. An agent can easily differentiate between these two unrelated domains.

Naming Consistency3/5

The naming is mixed with no consistent pattern. CulturalEventInfo uses a descriptive noun phrase format, while KoreaSeoulSubwayStatus follows a different descriptive naming style. Both are readable but lack a consistent verb_noun or other predictable convention across the set.

Tool Count2/5

With only 2 tools, this server feels severely under-scoped for what appears to be a general 'Seoul Public Data' server. The tools cover two specific data endpoints, but the server name suggests broader public data access that would typically require more comprehensive coverage of Seoul's public data APIs.

Completeness2/5

Given the server name 'Seoul Public Data MCP Server,' there are significant gaps in coverage. Seoul likely offers numerous public data APIs beyond just cultural events and subway passenger counts. The surface is severely incomplete for what the server name promises, with no coverage of transportation, weather, demographics, or other typical public data domains.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • 네이버 길찾기 MCP 서버

    Chaeyun06
    -
    license
    A
    quality
    Not graded
    maintenance
    Enables users to access Naver Maps API functionality including directions, place search, geocoding, and reverse geocoding through a Model Context Protocol server.
    4
    -

  • k-skill-korea

    taeyoung1005
    F
    license
    Not graded
    quality
    B
    maintenance
    A read-only MCP server providing access to various Korean public data such as subway arrivals, weather, fine dust, bike availability, real estate, and more.
    -

  • Disclosure Compass

    MLOpsEngineer
    A
    license
    Not graded
    quality
    B
    maintenance
    A Model Context Protocol server that exposes seven read-only tools for querying Korean public company disclosures from the OpenDART system, returning normalized JSON.
    MIT

  • pubdata-mcp

    jcyeom
    F
    license
    A
    quality
    C
    maintenance
    Enables querying Korean public datasets (apartment prices, weather, air quality) via natural language using an MCP server and local LLM agent.
    5
    -

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pinnaclesoft-ko/be-node-seoul-data-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server