Skip to main content
Glama
isnow890

Naver Search MCP Server

search_webkr

Query and retrieve relevant web documents from Naver Search. Specify search terms, sort results by similarity or date, and customize display options for targeted content discovery.

Instructions

Perform a search on Naver Web Documents. (네이버 웹문서 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

  • The primary handler function that performs the 'webkr' search by calling the NaverSearchClient.search method with target 'webkr'.
    export async function handleWebKrSearch(args: SearchArgs) {
      const client = NaverSearchClient.getInstance();
      return await client.search("webkr", args);
    }
  • Wrapper handler registered in searchToolHandlers that logs input arguments, validates them using SearchArgsSchema, and delegates to the core handleWebKrSearch function.
    search_webkr: (args) => {
      console.error("search_webkr called with args:", JSON.stringify(args, null, 2));
      return handleWebKrSearch(SearchArgsSchema.parse(args));
  • src/index.ts:102-115 (registration)
    MCP server tool registration for 'search_webkr', specifying description, input schema, and execution handler that calls searchToolHandlers and formats response as text content.
    server.registerTool(
      "search_webkr",
      {
        description:
          "🌐 Search Korean web documents and general content. Comprehensive search across Korean websites and online content. Find articles, information, and documents from various Korean sources. For recent content or 'today's results', use get_current_korean_time first. (네이버 웹문서 검색 - 한국 웹사이트 종합 검색, 최근 콘텐츠나 오늘 결과를 찾을 때는 먼저 get_current_korean_time으로 현재 시간을 확인하세요)",
        inputSchema: SearchArgsSchema.shape,
      },
      async (args) => {
        const result = await searchToolHandlers.search_webkr(args);
        return {
          content: [{ type: "text", text: JSON.stringify(result, null, 2) }],
        };
      }
    );
  • Zod schema defining the input parameters (query, display, start, sort) for the search_webkr tool and other search tools, used for validation in the handler.
    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)"),
    });
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 of behavioral disclosure. It states the tool performs a search, implying it's a read-only operation, but doesn't cover aspects like rate limits, authentication needs, error handling, or what the output looks like (e.g., result format, pagination). For a search tool with no annotation coverage, this leaves significant gaps in understanding its behavior.

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

Conciseness5/5

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

The description is extremely concise and front-loaded, consisting of a single sentence with a clear purpose statement and a helpful Korean translation. There's no wasted text, and it efficiently communicates the core function without unnecessary details, making it easy to scan and understand quickly.

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?

Given the complexity of a search tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., search results format, error responses) or address behavioral aspects like performance or limitations. With 4 parameters and many sibling tools, more context is needed to guide effective use, leaving gaps in overall understanding.

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, with clear documentation for all four parameters (query, display, sort, start). The description doesn't add any additional meaning beyond what's in the schema, such as explaining the 'sim' and 'date' sort options further or providing usage examples. Since schema coverage is high, the baseline score of 3 is appropriate, as the schema does the heavy lifting.

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: 'Perform a search on Naver Web Documents' with the Korean translation for clarity. It specifies the verb 'search' and the resource 'Naver Web Documents,' making it easy to understand what the tool does. However, it doesn't explicitly differentiate from siblings like 'search_blog' or 'search_news,' which are also search tools on the same platform.

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. With many sibling tools like 'search_blog,' 'search_news,' and 'search_academic,' it's unclear what makes 'search_webkr' unique or when it should be chosen over others. There's no mention of context, exclusions, or specific use cases.

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