Searches for places with matching category group code
AI agents call search_by_category to retrieve information from MCP Kakao Local without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves place information based on category filtering, which is a read-only operation consistent with search functionality. It has no side effects, does not create or modify data, does not execute code, and does not involve financial transactions.
From the tool's definition Tool is explicitly described as 'Searches for places with matching category group code' - a pure query operation that retrieves location data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Searches for places with matching category group code. It is categorised as a Read tool in the MCP Kakao Local MCP Server, which means it retrieves data without modifying state.
Register the MCP Kakao Local MCP server in PolicyLayer and add a rule for search_by_category: 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 MCP Kakao Local. Nothing to install.
search_by_category 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 search_by_category 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 search_by_category. 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.
search_by_category is provided by the MCP Kakao Local MCP server (yunkee-lee/mcp-kakao-local). 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 →