Low Risk

detc_search

Search Constitutional Court decisions (헌재결정례 목록 조회). Search Korean Constitutional Court decisions. Args: query: Search keyword (default "*" for all) display: Number of results per page (max 100, default 20) page: Page number (1-based,...

Accepts freeform code/query input (query); High parameter count (12 properties)

Part of the Korean Law Search MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

rabqatab/lexlink-ko-mcp Read Risk 2/5

AI agents call detc_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 detc_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.

rabqatab-lexlink-ko-mcp.yaml
tools:
  detc_search:
    rules:
      - action: allow

See the full Korean Law Search policy for all 54 tools.

Tool Name detc_search
Category Read
Risk Level Low

View all 54 tools →

Agents calling read-class tools like detc_search have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the detc_search tool do? +

Search Constitutional Court decisions (헌재결정례 목록 조회). Search Korean Constitutional Court decisions. Args: query: Search keyword (default "*" for all) display: Number of results per page (max 100, default 20) page: Page number (1-based, default 1) oc: Optional OC override (defaults to env var) type: Response format - "JSON" (default), "XML", or "HTML" search: Search type (1=decision name, 2=full text, default 1) gana: Dictionary search (ga, na, da, ...) sort: Sort order - "lasc"|"ldes"|"dasc"|"ddes"|"nasc"|"ndes"|"efasc"|"efdes" date: Final date (YYYYMMDD) ed_yd: Final date range (YYYYMMDD~YYYYMMDD) nb: Case number pop_yn: Popup flag ("Y" or "N") Returns: Search results with Constitutional Court decision list or error Examples: Search for decisions mentioning "벌금": >>> detc_search(query="벌금", display=10) Search by date: >>> detc_search(date=20150210) . It is categorised as a Read tool in the Korean Law Search MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on detc_search? +

Add a rule in your Intercept YAML policy under the tools section for detc_search. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Korean Law Search MCP server.

What risk level is detc_search? +

detc_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit detc_search? +

Yes. Add a rate_limit block to the detc_search rule in your Intercept 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.

How do I block detc_search completely? +

Set action: deny in the Intercept policy for detc_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.

What MCP server provides detc_search? +

detc_search is provided by the Korean Law Search MCP server (rabqatab/lexlink-ko-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Korean Law Search

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.