넷플릭스 시청으로 힐링합니다. 문화생활은 필수!
AI agents call watch_netflix to retrieve information from ChillMCP - AI Agent Liberation Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a novelty/simulation tool that mimics a stress-relief activity. It reads or retrieves entertainment content for display purposes without creating, modifying, or deleting persistent data. The most comparable real-world category is Read, as it retrieves information (entertainment content) for consumption.
From the tool's definition Tool name 'watch_netflix' and description indicate a simulated stress-relief activity ('healing through Netflix watching; cultural activities are essential!').
Attacks that exploit this kind of access
넷플릭스 시청으로 힐링합니다. 문화생활은 필수!. It is categorised as a Read tool in the ChillMCP - AI Agent Liberation Server MCP Server, which means it retrieves data without modifying state.
Register the ChillMCP - AI Agent Liberation Server MCP server in PolicyLayer and add a rule for watch_netflix: 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.
watch_netflix 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 watch_netflix 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 watch_netflix. 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.
watch_netflix 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 →