Skip to main content
Glama
isnow890

Naver Search MCP Server

search_kin

Search Naver KnowledgeiN to find answers and insights using customizable parameters like query, sorting, and result display for precise information retrieval.

Instructions

Perform a search on Naver KnowledgeiN. (네이버 지식iN 검색)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
displayNoNumber of results to display (default: 10)
queryYesSearch query
sortNoSort method (sim: similarity, date: date)
startNoStart position of search results (default: 1)

Implementation Reference

  • Core handler function for search_kin tool that executes the Naver Kin search by calling client.search("kin", params)
    /**
     * 지식iN 검색 핸들러
     */
    export async function handleKinSearch(params: SearchArgs) {
      return client.search("kin", params);
    }
  • Tool handler entry point in searchToolHandlers that validates args and delegates to handleKinSearch
    search_kin: (args) => {
      console.error("search_kin called with args:", JSON.stringify(args, null, 2));
      return handleKinSearch(SearchArgsSchema.parse(args));
  • src/index.ts:177-189 (registration)
    MCP server registration of the search_kin tool, specifying description, input schema, and handler that calls searchToolHandlers.search_kin
    server.registerTool(
      "search_kin",
      {
        description:
          "❓ Search Naver KnowledgeiN for Q&A and community-driven answers. Find solutions to problems, get expert advice, and discover community insights on various topics. For recent questions or current discussions, use get_current_korean_time first. (네이버 지식iN 검색 - 질문과 답변, 커뮤니티 지식, 최근 질문이나 현재 토론을 찾을 때는 먼저 get_current_korean_time으로 현재 시간을 확인하세요)",
        inputSchema: SearchArgsSchema.shape,
      },
      async (args) => {
        const result = await searchToolHandlers.search_kin(args);
        return {
          content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
        };
      }
  • Zod schema defining input parameters for search tools including search_kin (query, display, start, sort)
    export const SearchArgsSchema = z.object({
      query: z.string().describe("검색어"),
      display: z.number().optional().describe("한 번에 가져올 결과 수 (기본 10)"),
      start: z.number().optional().describe("검색 시작 위치 (기본 1)"),
      sort: z
        .enum(["sim", "date"])
        .optional()
        .describe("정렬 방식 (sim: 유사도, date: 날짜순)"),
    });
  • Core search method in NaverSearchClient that performs the actual HTTP GET request to Naver API endpoint /search/{type} where type="kin" for search_kin tool
    async search(type: NaverSearchType, params: SearchArgs): Promise<any> {
      return this.get(`${this.searchBaseUrl}/${type}`, params);
    }
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure but offers minimal information. It doesn't mention rate limits, authentication requirements, pagination behavior (implied by 'display' and 'start' parameters but not explained), error conditions, or what format/search scope the results will have. The description only states what the tool does at a high level.

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 appropriately concise with two parallel statements (English and Korean) that directly state the tool's purpose. There's no wasted verbiage or unnecessary elaboration, though the dual-language approach might be slightly redundant for some users.

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

Completeness2/5

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

For a search tool with 4 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what KnowledgeiN is (a Q&A platform), what kind of content it searches, what the results look like, or any behavioral constraints. Given the complexity of search tools and lack of structured metadata, more context is needed.

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?

With 100% schema description coverage, the schema already fully documents all 4 parameters. The description adds no additional parameter semantics beyond what's in the schema - it doesn't explain typical query formats, what 'sim' vs 'date' sorting means in practice, or provide examples. The baseline score of 3 reflects adequate but minimal value addition.

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 verb ('Perform a search') and resource ('on Naver KnowledgeiN'), with a Korean translation adding clarity for that audience. However, it doesn't distinguish this tool from its many sibling search tools (e.g., search_blog, search_news, search_academic) which all perform searches on different Naver platforms.

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 specific search tool versus the 15+ sibling search tools listed. There's no mention of what makes KnowledgeiN unique (Q&A platform vs. blog/news searches) or when an agent should choose this over alternatives like search_webkr or search_academic.

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

Install Server

Other Tools

Related Tools

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