Take a screenshot and return it as a base64-encoded PNG.
AI agents call screenshot to retrieve information from ComputerMate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshot is a read-only operation that captures the current state of the display and returns it as encoded image data. It does not modify system state, execute code, delete data, or involve financial operations. The main risk is information disclosure if sensitive data is visible on screen, but this is a fundamental property of screen capture, not a misuse scenario.
From the tool's definition Tool "screenshot" description states it will "Take a screenshot and return it as a base64-encoded PNG." This retrieves visual data from the screen with no modification or side effects.
Attacks that exploit this kind of access
Take a screenshot and return it as a base64-encoded PNG. It is categorised as a Read tool in the ComputerMate MCP Server, which means it retrieves data without modifying state.
Register the ComputerMate MCP server in PolicyLayer and add a rule for 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 ComputerMate. Nothing to install.
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 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 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.
screenshot is provided by the ComputerMate MCP server (one710/computermate). 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 →