Take a screenshot of the current page. Returns a PNG image.
AI agents call cloak_screenshot to retrieve information from CloakBrowser MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots are read-only operations that capture visual state without altering the browser, application, or underlying data. The tool retrieves visual information only. While the CloakBrowser context involves bot-detection evasion (which raises ethical concerns), the technical classification of this specific tool remains Read because it performs passive data retrieval.
From the tool's definition Takes a screenshot of the current page and returns a PNG image — a passive observation action with no side effects, state changes, or data modifications.
Attacks that exploit this kind of access
Take a screenshot of the current page. Returns a PNG image. It is categorised as a Read tool in the CloakBrowser MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CloakBrowser MCP Server MCP server in PolicyLayer and add a rule for cloak_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 CloakBrowser MCP Server. Nothing to install.
cloak_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 cloak_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 cloak_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.
cloak_screenshot is provided by the CloakBrowser MCP Server MCP server (miwoomiwoo/cloakbrowser-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 →