게시판 글의 상세 내용을 조회합니다. postId는 nworks_board_posts로 조회 가능. User OAuth 인증 필요 (board.read scope)
AI agents call nworks_board_read to retrieve information from Nworks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves detailed post content from a NAVER WORKS board. It performs a query operation with no side effects—no data is created, modified, deleted, or executed. The read-only scope permission confirms this is a safe retrieval operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description states '게시판 글의 상세 내용을 조회합니다' (retrieves detailed content of board posts). The verb '조회' means 'to query/retrieve' with no modification or deletion of data. Requires 'board.read' scope, indicating read-only access.
Documented attack patterns abuse exactly the kind of access nworks_board_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nworks, and nothing reaches the server without passing your rules. This is the rule we recommend for nworks_board_read:
{
"version": "1",
"default": "deny",
"tools": {
"nworks_board_read": {}
}
}nworks_board_read is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
게시판 글의 상세 내용을 조회합니다. postId는 nworks_board_posts로 조회 가능. User OAuth 인증 필요 (board.read scope). It is categorised as a Read tool in the Nworks MCP Server, which means it retrieves data without modifying state.
Register the Nworks MCP server in PolicyLayer and add a rule for nworks_board_read: 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 Nworks. Nothing to install.
nworks_board_read 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 nworks_board_read 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 nworks_board_read. 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.
nworks_board_read is provided by the Nworks MCP server (yjcho9317/nworks). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nworks, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
26 Nworks tools catalogued and risk-classified — across an index of 43,000+ MCP servers.