Skip to main content
Glama
yunkee-lee

MCP Kakao Local

by yunkee-lee

get_place

Retrieve comprehensive place details including name, address, reviews, and photos using a place ID from Kakao Local search results.

Instructions

Fetches details for a place such as name, address, reviews, photos and etc

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
place_idYesID of a place, which is document ID in location search results

Implementation Reference

  • The handler function for the 'get_place' MCP tool. It is registered with @mcp.tool and handles input validation via Pydantic Field, then delegates to KakaoLocalClient.get_place_details.
    @mcp.tool(description="Fetches details for a place such as name, address, reviews, photos and etc")
    async def get_place(
      place_id: int = Field(
        description="ID of a place, which is document ID in location search results", ge=1
      ),
    ) -> dict:
      """
      Returns:
        PlaceDetailResponse: An object containing details of the place
      """
      try:
        return await kakao_local_client.get_place_details(place_id)
      except Exception as ex:
        return {"success": False, "error": str(ex)}
  • The core helper function that performs the HTTP request to Kakao's place API to fetch detailed information for the given place_id and parses it into PlaceDetailResponse.
    async def get_place_details(self, place_id: int) -> PlaceDetailResponse:
      headers = {
        "Accept": "application/json, text/plain, */*",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "en-US,en;q=0.9",
        "Connection": "keep-alive",
        "Dnt": "1",
        "Origin": "https://place.map.kakao.com",
        "Referer": "https://place.map.kakao.com/",
        "Pf": "web",
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36",
      }
      async with httpx.AsyncClient(headers=headers, http2=True) as client:
        response = await client.get(f"https://place-api.map.kakao.com/places/panel3/{place_id}")
        try:
          response_json = response.raise_for_status().json()
          return PlaceDetailResponse(**response_json)
        except httpx.HTTPError as exc:
          self._handle_response_status(response.status_code, exc)
  • Pydantic model defining the output schema for place details, used by the get_place_details helper.
    class PlaceDetailResponse(BaseModel):
      menu: dict = Field({}, description="Menus if the place has menus")
      summary: PlaceSummary = Field(description="Summary of the place")
      business_hours: dict = Field(description="Details of business hours")
      photos: dict = Field(description="Contains counts (metadata) and photos of the place")
      blog_review: dict = Field(description="Review of the place in blogs")
      kakaomap_review: dict = Field(description="Review of the place on Kakap Map (optional)")
      find_way: dict = Field(description="Transit information nearby the place")
      place_add_info: dict = Field(description="Additional information of the place")
  • The @mcp.tool decorator registers the 'get_place' function as an MCP tool with its description.
    @mcp.tool(description="Fetches details for a place such as name, address, reviews, photos and etc")
  • Input schema validation for the place_id parameter using Pydantic Field.
    place_id: int = Field(
      description="ID of a place, which is document ID in location search results", ge=1
    ),
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 fetches details but doesn't describe the return format, pagination, error handling, rate limits, or authentication needs. For a read operation with zero annotation coverage, this is a significant gap in transparency.

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 a single, efficient sentence that front-loads the key action and resource. It avoids unnecessary words, though it could be slightly more structured (e.g., by listing details more clearly). Every part of the sentence contributes to understanding the tool's purpose.

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 lack of annotations and output schema, the description is incomplete. It doesn't explain what the return values look like (e.g., structure of details like reviews or photos), error cases, or behavioral traits. For a tool that fetches potentially complex data, this leaves significant gaps for the agent.

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% coverage, fully documenting the single parameter 'place_id' with its description, type, and constraints. The description adds no additional parameter information beyond what the schema provides, such as examples or context for obtaining the ID. Baseline 3 is appropriate when 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 action ('fetches details') and resource ('a place'), specifying what information is retrieved (name, address, reviews, photos, etc.). It distinguishes from sibling tools like 'find_coordinates' or 'search_by_category' by focusing on retrieving details for a specific place rather than searching or locating. However, it doesn't explicitly differentiate from potential siblings that might also fetch place details, keeping it at 4.

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 doesn't mention prerequisites (e.g., needing a place_id from search results), exclusions, or comparisons to sibling tools like 'search_by_keyword' for initial lookup. This lack of context leaves the agent without clear usage instructions.

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