Take a screenshot of the current page
AI agents call take_screenshot to retrieve information from Mcp Webresearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Taking a screenshot is a read-only operation that retrieves the visual state of a page. It has no side effects on external systems or data. The only concern is potential exposure of sensitive information visible on screen, but the act itself is non-destructive and non-modifying.
From the tool's definition 'Take a screenshot of the current page' — captures a visual snapshot of the currently loaded page without modifying or deleting any data.
Attacks that exploit this kind of access
Take a screenshot of the current page. It is categorised as a Read tool in the Mcp Webresearch MCP Server, which means it retrieves data without modifying state.
Register the Mcp Webresearch 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 Mcp Webresearch. 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 Mcp Webresearch MCP server (@mzxrai/mcp-webresearch). 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 →