Skip to main content
Glama
jikime

Naver Search MCP Server

search_shop

Find shopping products on Naver by entering keywords. Filter results by relevance, date, or price, and navigate through pages to compare options.

Instructions

Searches for shopping product information on Naver using the given keyword. The page parameter allows for page navigation and sort='sim'/'date'/'asc'/'dsc' is supported.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
displayNo
pageNo
sortNosim

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Full handler implementation for the 'search_shop' MCP tool, including decorator registration, parameter handling, pagination calculation, and invocation of the shared Naver API caller with shop-specific endpoint and schema.
    @mcp.tool(
      name="search_shop",
      description="Searches for shopping product information on Naver using the given keyword. The page parameter allows for page navigation and sort='sim'/'date'/'asc'/'dsc' is supported."
    )
    async def search_shop(query: str, display: int = 10, page: int = 1, sort: str = "sim") -> str:
        """
        Searches for shopping product information on Naver using the given keyword. The page parameter allows for page navigation and sort='sim'/'date'/'asc'/'dsc' is supported.
    
        Args:
            query (str): The keyword to search for
            display (int, optional): The number of results to display. Default is 10.
            page (int, optional): The starting page number. Default is 1.
            sort (str, optional): The sorting criteria. Default is "sim" (similarity).
        """
        start = calculate_start(page, display)
        display = min(display, 100)
        params = {"query": query, "display": display, "start": start, "sort": sort}
        return await _make_api_call("shop.json", params, ShopResult, "Shopping")
  • Pydantic model defining the structure of individual shop search result items, used in ShopResult.
    class ShopItem(BaseItem):
        image: Optional[str] = None
        lprice: Optional[str] = None
        hprice: Optional[str] = None
        mallName: Optional[str] = None
        productId: Optional[str] = None
        productType: Optional[str] = None
        maker: Optional[str] = None
        brand: Optional[str] = None
        category1: Optional[str] = None
        category2: Optional[str] = None
        category3: Optional[str] = None
        category4: Optional[str] = None
  • Pydantic model for the complete shop search response from Naver API, extending SearchResultBase with List[ShopItem].
    class ShopResult(SearchResultBase): items: List[ShopItem]
  • ShopItem-specific field formatting logic within the shared _make_api_call helper function, which formats API responses into readable text.
    if hasattr(item, 'image') and item.image:
        text_result += f"이미지(image): {item.image}\n"
    if hasattr(item, 'lprice') and item.lprice:
        text_result += f"최저가(lprice): {item.lprice}\n"
    if hasattr(item, 'hprice') and item.hprice:
        text_result += f"최고가(hprice): {item.hprice}\n"
    if hasattr(item, 'mallName') and item.mallName:
        text_result += f"쇼핑몰명(mallName): {item.mallName}\n"
    if hasattr(item, 'brand') and item.brand:
        text_result += f"브랜드(brand): {item.brand}\n"
    if hasattr(item, 'maker') and item.maker:
        text_result += f"제조사(maker): {item.maker}\n"
    if hasattr(item, 'category1') and item.category1:
        text_result += f"카테고리1(category1): {item.category1}\n"
    if hasattr(item, 'category2') and item.category2:
        text_result += f"카테고리2(category2): {item.category2}\n"
    if hasattr(item, 'category3') and item.category3:
        text_result += f"카테고리3(category3): {item.category3}\n"
    if hasattr(item, 'category4') and item.category4:
        text_result += f"카테고리4(category4): {item.category4}\n"
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions that 'page parameter allows for page navigation' and 'sort='sim'/'date'/'asc'/'dsc' is supported,' which adds some operational context. However, it doesn't cover important behavioral aspects like rate limits, authentication requirements, error handling, or what the output contains. For a search tool with no annotation coverage, this leaves significant gaps.

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 sentences that each add value. The first sentence establishes the core purpose, and the second provides important parameter details. There's no wasted language, and information is front-loaded with the main function stated first.

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 that there's an output schema (which means the description doesn't need to explain return values) and no annotations, the description provides basic operational context but leaves gaps. It covers the main purpose and some parameter semantics, but doesn't address behavioral aspects like rate limits or error conditions. For a search tool with 4 parameters and no annotations, this is minimally adequate but could be more comprehensive.

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

Parameters4/5

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

The description adds meaningful context beyond the input schema. While the schema has 0% description coverage (only titles), the description explains that 'page parameter allows for page navigation' and specifies valid sort values ('sim'/'date'/'asc'/'dsc'). This clarifies the purpose of the 'page' and 'sort' parameters that the schema only lists by title. However, it doesn't explain the 'display' parameter or provide examples for the 'query' parameter.

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: 'Searches for shopping product information on Naver using the given keyword.' This specifies the verb ('searches'), resource ('shopping product information'), and platform ('Naver'), making it easy to understand what the tool does. However, it doesn't explicitly differentiate from sibling tools like 'search_blog' or 'search_news' beyond mentioning 'shopping product information'.

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 'shopping product information' which implies a context, but doesn't specify when to choose this over other search tools like 'search_webkr' or 'search_local'. There's no mention of prerequisites, exclusions, or comparative use cases with sibling tools.

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

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/jikime/py-mcp-naver-search'

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