take_screenshot
AI agents call take_screenshot to retrieve information from Computer Control Mcp Lands without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Taking a screenshot retrieves visual information from the screen with no state changes or side effects. This is a read-only operation. While it could reveal sensitive information on-screen, the tool itself performs no destructive, modifying, or executable action. Severity is low because screenshot capture alone does not directly compromise systems or data integrity—though context matters in actual deployment.
From the tool's definition Tool name 'take_screenshot' and server description indicating 'screen capture' capabilities. The description field is empty, but the name and context clearly indicate data retrieval without side effects.
Attacks that exploit this kind of access
take_screenshot. It is categorised as a Read tool in the Computer Control Mcp Lands MCP Server, which means it retrieves data without modifying state.
Register the Computer Control Mcp Lands MCP server in PolicyLayer and add a rule for take_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 Computer Control Mcp Lands. Nothing to install.
take_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 take_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 take_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.
take_screenshot is provided by the Computer Control Mcp Lands MCP server (songcaiya/windows-mcp-lands). 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 →