Take a screenshot of any webpage. Returns a base64-encoded image.
AI agents call take_screenshot to retrieve information from PageShot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation: it fetches a webpage and returns a visual representation as a base64 image. It does not create, modify, delete, or trigger any external state changes. The only concern would be if it accessed sensitive internal URLs, but the action itself is non-destructive and reversible.
From the tool's definition 'Take a screenshot of any webpage. Returns a base64-encoded image.' — the tool only reads/captures a visual snapshot of a webpage and returns data, with no side effects.
Attacks that exploit this kind of access
Take a screenshot of any webpage. Returns a base64-encoded image. It is categorised as a Read tool in the PageShot MCP MCP Server, which means it retrieves data without modifying state.
Register the PageShot 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 PageShot MCP. 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 PageShot MCP server (pageshot-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 →