Skip to main content
Glama
yunkee-lee

MCP Kakao Local

by yunkee-lee

find_coordinates

Convert addresses to geographic coordinates using Kakao Local API for location-based services and mapping in Korea.

Instructions

Find coordinates of a given address

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
addressYesaddress to search for
pageNopage number of result

Implementation Reference

  • MCP tool handler for find_coordinates: validates inputs with Pydantic Fields, calls KakaoLocalClient.find_coordinates, handles empty results and exceptions, returns AddressResponse or error dict.
    @mcp.tool(description="Find coordinates of a given address")
    async def find_coordinates(
      address: str = Field(description="address to search for", min_length=1),
      page: int = Field(1, description="page number of result", ge=1),
    ) -> AddressResponse:
      """
      Returns:
        AddressResponse: An object containing metadata and a list of addresses
      """
      try:
        response = await kakao_local_client.find_coordinates(address, page=page)
        if len(response.documents) == 0:
          return {"success": False, "error": "No coordinates found. Check if the address is correct."}
    
        return response
      except Exception as ex:
        return {"success": False, "error": str(ex)}
  • Core implementation in KakaoLocalClient: constructs API params, makes HTTP GET to Kakao Local API endpoint for address coordinates, parses JSON response into AddressResponse model.
    async def find_coordinates(self, address: str, page: int = 1, size: int = 10) -> AddressResponse:
      """https://developers.kakao.com/docs/latest/ko/local/dev-guide#address-coord"""
      path = f"{self.BASE_URL}/search/address"
      params = {
        "query": address,
        "page": page,
        "size": size,
      }
      response_json = await self._get(path, params)
      return AddressResponse(**response_json)
  • Pydantic BaseModel schema for the tool's output: AddressResponse containing meta (paging info) and list of AddressDocument (each with address_name, type, x/y coordinates, etc.).
    class AddressResponse(BaseModel):
      meta: Meta = Field(description="Response metadata")
      documents: list[AddressDocument] = Field(description="List of addresses")
  • Registration of the 'find_coordinates' tool via FastMCP's @mcp.tool decorator with description.
    @mcp.tool(description="Find coordinates of a given address")
  • Pydantic model for individual address document in response: includes address_name, type, longitude (x), latitude (y), and address details.
    class AddressDocument(BaseModel):
      address_name: str = Field(description="street address or land-lot address (지번 주소)")
      address_type: Literal["REGION", "ROAD", "REGION_ADDR", "ROAD_ADDR"] = Field(
        description="type of address"
      )
      x: str = Field(description="longitude")
      y: str = Field(description="latitude")
      address: dict = Field(description="details of land-lot address (지번 주소)")
      road_address: dict = Field(description="details of street address")
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 action ('find coordinates') but doesn't describe traits like whether it's read-only, if it requires authentication, rate limits, error handling, or the format of returned coordinates. This leaves significant gaps for a tool with no structured safety hints.

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 directly states the tool's purpose without unnecessary words. It's front-loaded and appropriately sized, making it easy for an agent to parse 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 no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., coordinates format, error cases), behavioral traits, or usage context relative to siblings. For a tool with 2 parameters and potential complexity in geocoding, this leaves the agent under-informed.

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?

Schema description coverage is 100%, so the input schema already documents both parameters ('address' and 'page') with descriptions. The description adds minimal value beyond implying the 'address' parameter is used for searching, but doesn't provide additional context like address format examples or pagination behavior, meeting the baseline for high schema coverage.

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 with a specific verb ('find') and resource ('coordinates'), and specifies the input ('address'). However, it doesn't differentiate from sibling tools like 'get_place' or 'search_by_category', which might have overlapping functionality for location-related queries.

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 'get_place' or 'search_by_category'. It lacks context about prerequisites, such as address format expectations, or exclusions, leaving the agent to infer usage based on the tool name alone.

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-kakao-local'

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