관보 원본에서 키워드(주식 종목명, 부동산 지역, 금융기관, 가상자산 등)를 전문 검색하여 해당 재산을 보유한 공직자를 찾습니다. 예시 질문: - "엔비디아를 가진 공직자는?" - "테슬라 주식 보유 공직자" - "비트코인 보유 공직자" - "강남구 부동산 보유 공직자" Args: - keyword (string): 검색 키워드 (최소 2자) - year (string, optional): 연도 (미지정 시 최신) - format ('markdown' | 'json'): 출력 형식 Returns:...
Part of the Public Official MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call pety_search_by_keyword to retrieve information from Public Official 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 pety_search_by_keyword 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.
tools:
pety_search_by_keyword:
rules:
- action: allowSee the full Public Official policy for all 4 tools.
Agents calling read-class tools like pety_search_by_keyword have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
관보 원본에서 키워드(주식 종목명, 부동산 지역, 금융기관, 가상자산 등)를 전문 검색하여 해당 재산을 보유한 공직자를 찾습니다. 예시 질문: - "엔비디아를 가진 공직자는?" - "테슬라 주식 보유 공직자" - "비트코인 보유 공직자" - "강남구 부동산 보유 공직자" Args: - keyword (string): 검색 키워드 (최소 2자) - year (string, optional): 연도 (미지정 시 최신) - format ('markdown' | 'json'): 출력 형식 Returns: 키워드가 포함된 재산을 보유한 공직자 목록 (이름, 소속, 직위, 관보 페이지). It is categorised as a Read tool in the Public Official MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for pety_search_by_keyword. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Public Official MCP server.
pety_search_by_keyword 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 pety_search_by_keyword 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.
Set action: deny in the Intercept policy for pety_search_by_keyword. 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.
pety_search_by_keyword is provided by the Public Official MCP server (public-official-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept