Take a screenshot of the current page
AI agents call screenshot_capture to retrieve information from MCP Browser Screenshot Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads the current visual state of a browser page and captures it as an image. It has no side effects on external systems or data. The only risk is that it could capture sensitive information displayed in the browser, but it does not modify, execute, or destroy anything itself. Severity is low as misuse is limited to information disclosure of whatever is currently rendered.
From the tool's definition 'Take a screenshot of the current page' — captures visual state, no data modification
Attacks that exploit this kind of access
Take a screenshot of the current page. It is categorised as a Read tool in the MCP Browser Screenshot Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Browser Screenshot Server MCP server in PolicyLayer and add a rule for screenshot_capture: 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 Browser Screenshot Server. Nothing to install.
screenshot_capture 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_capture 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_capture. 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_capture is provided by the MCP Browser Screenshot Server MCP server (seabassgonzalez/mcp-browser-screenshot). 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 →