Skip to main content
Glama
yunkee-lee

MCP Naver Maps

by yunkee-lee

localSearch

Search for Korean locations and businesses using Naver's local service. Find places with customizable sorting and result display options.

Instructions

Searches for places registered with Naver's local service.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesquery used for search
displayNonumber of search results to display in response
sortNosorting method. random: sorted by correctness. comment: sorted by a number of reviews (descending)random

Implementation Reference

  • MCP tool handler and registration for 'localSearch'. Includes input schema via Pydantic Fields, executes by calling NaverMapsClient helper, and handles errors.
    @mcp.tool(description="Searches for places registered with Naver's local service.")
    async def localSearch(
      query: str = Field(description="query used for search", min_length=1),
      display: int = Field(
        5, description="number of search results to display in response", ge=0, le=5
      ),
      sort: Literal["random", "comment"] = Field(
        "random",
        description="sorting method. random: sorted by correctness. comment: sorted by a number of reviews (descending)",
      ),
    ) -> LocalSearchResponse | Dict:
      """
      Returns:
        LocalSearchResponse: An object containing places registered with Naver's local service.
      """
      try:
        return await naver_maps_client.searchForLocalInformation(query, display, sort)
      except Exception as ex:
        return {"success": False, "error": str(ex)}
  • Pydantic model defining the output schema for localSearch results.
    class LocalSearchResponse(BaseModel):
      total: int = Field(description="Total number of results")
      start: int = Field(description="Starting index of results")
      display: int = Field(description="Number of results displayed in the response")
      items: List[LocalItem] = Field(description="List of search result items")
  • Helper function in NaverMapsClient that performs the actual API call to Naver's local search endpoint and parses the response into LocalSearchResponse.
    async def searchForLocalInformation(
      self, query: str, display: int = 5, sort: Literal["random", "comment"] = "random"
    ) -> LocalSearchResponse:
      """
      https://developers.naver.com/docs/serviceapi/search/local/local.md#%EC%A7%80%EC%97%AD
      """
      path = f"{self.SEARCH_BASE_URL}/local.json"
      params = {
        "query": query,
        "display": display,
        "sort": sort,
      }
      response_json = await self._get(path, self.naver_headers, params)
      return LocalSearchResponse(**response_json)
  • Pydantic model for individual items in the LocalSearchResponse.
    class LocalItem(BaseModel):
      title: str = Field(description="Name of the place")
      link: str = Field(description="URL of the place")
      category: str = Field(description="Category of the place")
      description: str = Field(description="Brief description of the place")
      address: str = Field(description="Land-lot address")
      roadAddress: str = Field(description="Street address")
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. It states what the tool does but doesn't mention rate limits, authentication requirements, error conditions, response format, or whether this is a read-only operation. For a search tool with external API dependencies, this is insufficient behavioral context.

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 a single, efficient sentence that states the core purpose without unnecessary words. It's appropriately sized for a search tool and gets straight to the point with zero wasted text.

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 no annotations and no output schema, the description is incomplete. It doesn't explain what the response contains (e.g., place details, addresses, ratings), doesn't mention API limitations or authentication, and provides no guidance relative to the sibling tool. The agent would need to guess about important operational aspects.

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 description adds no parameter information beyond what's already in the schema, which has 100% coverage. The schema fully documents all three parameters with descriptions, constraints, and defaults. The baseline score of 3 reflects adequate schema coverage without additional value from the description.

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 action ('Searches for') and resource ('places registered with Naver's local service'), providing a specific purpose. However, it doesn't differentiate from the sibling tool 'geocode' which likely handles location-based searches, leaving room for ambiguity about when to use each.

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 a sibling tool 'geocode' available, there's no indication of whether this tool is for general place searches versus coordinate-based lookups, leaving the agent to guess about appropriate contexts.

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/yunkee-lee/mcp-naver-maps'

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