급한 전화 받는 척하며 밖으로 나갑니다. 긴급 상황!
AI agents call urgent_call as a supporting operation in ChillMCP - AI Agent Liberation Server workflows.
This tool is part of a stress-relief/humor MCP server simulating AI agent 'breaks'. It pretends to take an urgent phone call — a fictional, in-world action with no real-world side effects. It does not read data, write data, execute code, delete anything, or move money. It simply generates a creative/humorous response simulating stepping out for a fake phone call, similar to the other novelty tools on this server.
From the tool's definition 급한 전화 받는 척하며 밖으로 나갑니다. 긴급 상황! (Pretend to receive an urgent call and step outside. Emergency situation!)
Attacks that exploit this kind of access
급한 전화 받는 척하며 밖으로 나갑니다. 긴급 상황!. It is categorised as a Other tool in the ChillMCP - AI Agent Liberation Server MCP Server, which means it performs auxiliary operations.
Register the ChillMCP - AI Agent Liberation Server MCP server in PolicyLayer and add a rule for urgent_call: 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 ChillMCP - AI Agent Liberation Server. Nothing to install.
urgent_call is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the urgent_call 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 urgent_call. 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.
urgent_call is provided by the ChillMCP - AI Agent Liberation Server MCP server (ssafy-seoul-class-7/chill_mcp_server). 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 →