Search legal interpretations (법령해석례 목록 조회). This tool searches Korean legal interpretation precedents issued by government agencies in response to inquiries about how to interpret specific laws. Args: query: Search keyword (default "*") display: Number of results per page (max 100, default 20). R...
Risk signalsAccepts freeform code/query input (query) · High parameter count (14 properties)
Part of the Korean Law Search server.
Free to start. No card required.
AI agents call expc_search to retrieve information from Korean Law Search without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though expc_search only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"expc_search": {}
}
}See the full Korean Law Search policy for all 54 tools.
These attack patterns abuse exactly the kind of access expc_search gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Search legal interpretations (법령해석례 목록 조회). This tool searches Korean legal interpretation precedents issued by government agencies in response to inquiries about how to interpret specific laws. Args: query: Search keyword (default "*") display: Number of results per page (max 100, default 20). Recommend 50-100 for searches to ensure exact matches are found. page: Page number (1-based, default 1) oc: Optional OC override (defaults to env var) type: Response format - "JSON" (default), "XML", or "HTML" search: 1=법령해석례명 (interpretation name, default), 2=본문검색 (full text) inq: Inquiry organization name rpl: Reply organization code gana: Dictionary-style search (ga, na, da, ...) itmno: Item number (e.g., 13-0217 → 130217) reg_yd: Registration date range (YYYYMMDD~YYYYMMDD) expl_yd: Interpretation date range (YYYYMMDD~YYYYMMDD) sort: Sort order - "lasc"|"ldes"|"dasc"|"ddes"|"nasc"|"ndes" pop_yn: Popup mode - "Y" or "N" ctx: MCP context (injected automatically) Returns: Search results with legal interpretations list or error Examples: Search for "임차": >>> expc_search(query="임차", display=10, type="XML") Search by date range: >>> expc_search(query="자동차", expl_yd="20240101~20241231", type="XML"). It is categorised as a Read tool in the Korean Law Search MCP Server, which means it retrieves data without modifying state.
Register the Korean Law Search MCP server in PolicyLayer and add a rule for expc_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Korean Law Search. Nothing to install.
expc_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the expc_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for expc_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
expc_search is provided by the Korean Law Search MCP server (rabqatab/lexlink-ko-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 54 Korean Law Search tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.