スクショ取得 (studio=Robloxのみ、full=全画面、window=アクティブ、interactive=選択)
AI agents call captureScreen to retrieve information from Roblox Studio Ultimate MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Taking a screenshot is a read-only operation that captures the current visual state of the screen or a window. It has no side effects on data or system state. The blast radius of misuse is low — at worst it captures sensitive on-screen information.
From the tool's definition captureScreen / スクショ取得 — 'スクショ取得' means 'screenshot capture'; the options (studio, full screen, window, interactive) all describe reading/capturing visual state without modifying anything
Attacks that exploit this kind of access
スクショ取得 (studio=Robloxのみ、full=全画面、window=アクティブ、interactive=選択). It is categorised as a Read tool in the Roblox Studio Ultimate MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Roblox Studio Ultimate MCP Server MCP server in PolicyLayer and add a rule for captureScreen: 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 Roblox Studio Ultimate MCP Server. Nothing to install.
captureScreen 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 captureScreen 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 captureScreen. 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.
captureScreen is provided by the Roblox Studio Ultimate MCP Server MCP server (jundayoo/roblox-studio-ultimate-mcp). 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 →