Skip to main content
Glama
leadbrain

korean-data-mcp

search_naver_news

Search for Korean news articles on Naver News using a query, control the number of results (max 100), and sort by date or relevance.

Instructions

Search Naver News (네이버 뉴스) for Korean news articles.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query in Korean or English
max_articlesNoMaximum number of articles to return (default 20, max 100)
sortNoSort order — 'date' (최신순) or 'sim' (관련도순)date

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The handler function for the 'search_naver_news' tool. It is decorated with @mcp.tool() and accepts query (str), max_articles (int, default 20), and sort (str, default 'date'). It caps max_articles at 100 and delegates to the _run_actor helper to call the Apify 'naver-news-scraper' actor.
    @mcp.tool()
    async def search_naver_news(
        query: str,
        max_articles: int = 20,
        sort: str = "date",
    ) -> list[dict]:
        """
        Search Naver News (네이버 뉴스) for Korean news articles.
    
        Args:
            query: Search query in Korean or English
            max_articles: Maximum number of articles to return (default 20, max 100)
            sort: Sort order — 'date' (최신순) or 'sim' (관련도순)
    
        Returns:
            List of article objects with title, summary, source, date, url fields.
        """
        max_articles = min(max_articles, 100)
        return await _run_actor(
            f"{APIFY_ACCOUNT}/naver-news-scraper",
            {"query": query, "maxArticles": max_articles, "sort": sort},
        )
  • Input type definition / signature for search_naver_news: takes query (str), max_articles (int, default 20), sort (str, default 'date'), returns list[dict].
    async def search_naver_news(
        query: str,
        max_articles: int = 20,
        sort: str = "date",
    ) -> list[dict]:
  • Tool registration via @mcp.tool() decorator on the search_naver_news async function. FastMCP automatically registers the function as an MCP tool based on the decorator.
    @mcp.tool()
  • The _run_actor helper that runs an Apify actor and returns dataset items. Used by search_naver_news to call the 'naver-news-scraper' actor.
    async def _run_actor(actor_id: str, input_data: dict, timeout_secs: int = 60) -> list[dict]:
        """Run an Apify actor synchronously and return dataset items."""
        token = _get_token()
        url = f"{APIFY_BASE}/acts/{actor_id}/run-sync-get-dataset-items"
        params = {"token": token}
    
        async with httpx.AsyncClient(timeout=timeout_secs + 10) as client:
            resp = await client.post(url, json=input_data, params=params)
            resp.raise_for_status()
            return resp.json()
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 only states it 'searches' but does not mention whether it is read-only, any authentication requirements, rate limits, or what happens on error or empty results. The input schema adds some detail (sort, max_articles) but the description adds no behavioral context beyond the action.

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 sentence with no wasted words. It is front-loaded with the key action and resource. However, it is very brief and could benefit from a second sentence adding context (e.g., language scope) without being verbose.

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 tool has 3 parameters, no annotations, and an output schema (assumed defined), the description is too minimal. It lacks usage guidance, output format hints, and behavioral disclosures. While the schema covers parameters, the description does not integrate with the tool's operational context (e.g., when to use this vs other search tools).

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% description coverage, so parameters are already documented (query in Korean/English, max_articles range, sort options). The description adds no additional meaning beyond the schema. Baseline score of 3 is appropriate as 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 tool searches Naver News for Korean news articles. It distinguishes from sibling tools like search_bunjang (marketplace) and search_naver_places (places) by specifying the news domain. However, it could be more specific about the scope (e.g., only Korean-language articles) which is implied but not explicit.

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_bunjang or search_daangn. There are no exclusions, prerequisites, or context about typical use cases. Agents are left to infer from the name and 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/leadbrain/korean-data-mcp'

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