Skip to main content
Glama
isnow890

Naver Search MCP Server

datalab_shopping_by_age

Analyze Naver Shopping trends by age group, category, and time period to identify purchasing patterns and consumer preferences for targeted insights.

Instructions

Perform a trend analysis on Naver Shopping by age. (네이버 쇼핑 연령별 트렌드 분석)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agesYesAge groups
categoryYesCategory code
endDateYesEnd date (yyyy-mm-dd)
startDateYesStart date (yyyy-mm-dd)
timeUnitYesTime unit

Implementation Reference

  • Core handler function that processes the tool arguments and delegates to the NaverSearchClient's datalabShoppingByAge method
    export async function handleShoppingByAgeTrend(params: DatalabShoppingAge) {
      return client.datalabShoppingByAge({
        startDate: params.startDate,
        endDate: params.endDate,
        timeUnit: params.timeUnit,
        category: params.category,
        ages: params.ages,
      });
    }
  • Zod schema defining the input parameters for the datalab_shopping_by_age tool: category code and array of age groups (10-60) on top of base dates and timeUnit
    export const DatalabShoppingAgeSchema = DatalabBaseSchema.extend({
      category: z.string().describe("Category code"),
      ages: z
        .array(z.enum(["10", "20", "30", "40", "50", "60"]))
        .describe("Age groups"),
    });
  • src/index.ts:340-359 (registration)
    MCP server tool registration including name, description, inputSchema (derived from DatalabShoppingAgeSchema), and handler dispatcher to datalabToolHandlers
    server.registerTool(
      "datalab_shopping_by_age",
      {
        description:
          "👶👦👨👴 Analyze shopping trends by age groups (10s, 20s, 30s, 40s, 50s, 60s+). Use find_category first. BUSINESS CASES: Age-targeted products, generational preferences, lifecycle marketing. EXAMPLE: '개발 도구는 어느 연령대가 많이 구매하나?' For current age trends, use get_current_korean_time to set proper analysis period. (연령별 쇼핑 트렌드 - 먼저 find_category 도구로 카테고리 코드를 찾고, 현재 연령 트렌드 분석시 get_current_korean_time으로 적절한 분석 기간 설정)",
        inputSchema: DatalabShoppingAgeSchema.pick({
          startDate: true,
          endDate: true,
          timeUnit: true,
          category: true,
          ages: true,
        }).shape,
      },
      async (args) => {
        const result = await datalabToolHandlers.datalab_shopping_by_age(args);
        return {
          content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
        };
      }
    );
  • NaverSearchClient method that performs the actual POST request to Naver Datalab API endpoint for shopping trends by age
    async datalabShoppingByAge(
      params: DatalabShoppingAgeRequest
    ): Promise<DatalabShoppingResponse> {
      return this.post(`${this.datalabBaseUrl}/shopping/category/age`, params);
    }
  • Dispatcher entry in datalabToolHandlers map that logs args and calls the core handleShoppingByAgeTrend function
    datalab_shopping_by_age: (args) => {
      console.error("datalab_shopping_by_age called with args:", JSON.stringify(args, null, 2));
      return handleShoppingByAgeTrend(args);

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/isnow890/naver-search-mcp'

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