전체 화면을 캡처해서 이미지로 반환합니다. Claude가 직접 내용을 볼 수 있습니다.
AI agents call cc_screenshot to retrieve information from K-Personal MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screen capture is a passive data retrieval operation that reads visual information from the display without side effects. While it could expose sensitive information on the screen (reducing severity assessment), the tool itself performs no writes, executions, or destructive actions. It falls squarely into the Read category.
From the tool's definition Tool name 'cc_screenshot' and description state it captures the full screen and returns an image for Claude to view. This is a read-only operation with no modification, deletion, or execution of external commands.
Attacks that exploit this kind of access
전체 화면을 캡처해서 이미지로 반환합니다. Claude가 직접 내용을 볼 수 있습니다. It is categorised as a Read tool in the K-Personal MCP MCP Server, which means it retrieves data without modifying state.
Register the K-Personal MCP server in PolicyLayer and add a rule for cc_screenshot: 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 K-Personal MCP. Nothing to install.
cc_screenshot 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 cc_screenshot 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 cc_screenshot. 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.
cc_screenshot is provided by the K-Personal MCP server (lee30934-byte/k-personal-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 →