AI agents call greet to retrieve information from MCP Kkebi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The greet tool merely presents a welcome message to the user. It performs no queries, modifications, code execution, deletions, or financial operations. While it technically outputs information rather than retrieves it, it is functionally passive and non-invasive, making it the closest fit to the Read category as the least risky classification.
From the tool's definition Tool name 'greet' and description indicating it 'displays a welcome message to the user' (translated from Korean: '사용자에게 환영 메시지를 표시합니다'). This is a display/output operation with no data retrieval, modification, execution, or side effects.
Attacks that exploit this kind of access
사용자에게 환영 메시지를 표시합니다. It is categorised as a Read tool in the MCP Kkebi MCP Server, which means it retrieves data without modifying state.
Register the MCP Kkebi MCP server in PolicyLayer and add a rule for greet: 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 Kkebi. Nothing to install.
greet 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 greet 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 greet. 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.
greet is provided by the MCP Kkebi MCP server (mimsut/mcp_kkebi). 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 →