AI agents call get_screenshot to retrieve information from Computer Use without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves visual information from the screen with no side effects. It does not create, modify, delete, or execute anything—it only observes and returns data. This falls clearly under the Read category, with low severity since screenshots themselves pose minimal direct risk, though they could reveal sensitive information if the display contains it.
From the tool's definition Tool name 'get_screenshot' and description 'Take a screenshot of the virtual computer's display' indicate a read-only operation that captures the current state of the display without modifying anything.
Documented attack patterns abuse exactly the kind of access get_screenshot gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Computer Use, and nothing reaches the server without passing your rules. This is the rule we recommend for get_screenshot:
{
"version": "1",
"default": "deny",
"tools": {
"get_screenshot": {}
}
}get_screenshot is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Take a screenshot of the virtual computer's display. It is categorised as a Read tool in the Computer Use MCP Server, which means it retrieves data without modifying state.
Register the Computer Use MCP server in PolicyLayer and add a rule for get_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 Use. Nothing to install.
get_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 get_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 get_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.
get_screenshot is provided by the Computer Use MCP server (spencerkinney/computer-use-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Computer Use, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 Computer Use tools catalogued and risk-classified — across an index of 43,000+ MCP servers.