Skip to main content
Glama
jikime

Naver Search MCP Server

search_local

Find local businesses using keywords, with options to sort results by random or comment count and control display parameters.

Instructions

Searches for local business information using the given keyword. (display maximum 5, start maximum 1) sort='random'/'comment' is supported.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
displayNo
pageNo
sortNorandom

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The handler function that implements the core logic of the 'search_local' tool by preparing parameters and calling the shared Naver Local API via _make_api_call.
    async def search_local(query: str, display: int = 5, page: int = 1, sort: str = "random") -> str:
        """
        Searches for local business information using the given keyword. (display maximum 5, start maximum 1) sort='random'/'comment' is supported.
    
        Args:
            query (str): The keyword to search for
            display (int, optional): The number of results to display. Default is 5.
            page (int, optional): The starting page number. Default is 1.
            sort (str, optional): The sorting criteria. Default is "random" (random).
        """
        display = min(display, 5) # API 제약 조건 적용
        start = 1  # 지역 API는 항상 start=1
        params = {"query": query, "display": display, "start": start, "sort": sort}
        return await _make_api_call("local.json", params, LocalResult, "Local")
  • server.py:494-497 (registration)
    The @mcp.tool decorator that registers the 'search_local' tool with MCP, specifying its name and description.
    @mcp.tool(
      name="search_local",
      description="Searches for local business information using the given keyword. (display maximum 5, start maximum 1) sort='random'/'comment' is supported."
    )
  • Pydantic schema/model for individual local search result items, defining fields like category, address, telephone, etc.
    class LocalItem(BaseItem):
        category: Optional[str] = None
        description: Optional[str] = None
        telephone: Optional[str] = None
        address: Optional[str] = None
        roadAddress: Optional[str] = None
        mapx: Optional[str] = None
        mapy: Optional[str] = None
  • Pydantic schema for the overall Local search result, inheriting from SearchResultBase with items as List[LocalItem].
    class LocalResult(SearchResultBase): items: List[LocalItem]
Behavior2/5

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

With no annotations provided, the description carries full burden but offers minimal behavioral insight. It mentions display/page limits and sort options, but doesn't cover critical aspects like rate limits, authentication needs, error handling, or what the output contains. For a search tool with zero annotation coverage, this is inadequate.

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 brief but poorly structured: the parenthetical note about display/page is awkwardly placed and unclear. It's front-loaded with the core purpose, but the additional details are cryptic and could be better organized for clarity.

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 has an output schema (which handles return values), the description's gaps in parameter semantics and behavioral transparency are partially mitigated. However, for a search tool with 4 parameters and no annotations, it should provide more context on usage and limitations to be fully complete.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate but adds limited value. It explains that 'sort' supports 'random'/'comment', which isn't in the schema, but doesn't clarify 'query' semantics, 'display'/'page' constraints beyond maxima, or parameter interactions. With 4 parameters and poor coverage, this is insufficient.

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 ('searches for') and resource ('local business information'), making the purpose understandable. It doesn't explicitly differentiate from sibling tools like 'search_shop' or 'search_cafe_article', which might have overlapping domains, so it misses the highest score.

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 like search_shop or search_cafe_article. It mentions technical constraints (display maximum 5, start maximum 1) but doesn't explain the context or scenarios for choosing this tool over others.

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