Check if the search term is adult content
AI agents call adult_check to retrieve information from Naver MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and evaluates whether a search term is flagged as adult content. It has no side effects, makes no modifications to data, executes no code, and performs no destructive operations. The lowest blast radius applies: misuse would only affect classification results, not cause system damage or unintended execution.
From the tool's definition The tool 'adult_check' performs a check/validation operation on search terms to determine if they contain adult content.
Attacks that exploit this kind of access
Check if the search term is adult content. It is categorised as a Read tool in the Naver MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Naver MCP Server MCP server in PolicyLayer and add a rule for adult_check: 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 Naver MCP Server. Nothing to install.
adult_check 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 adult_check 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 adult_check. 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.
adult_check is provided by the Naver MCP Server MCP server (pfldy2850/py-mcp-naver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →