Capture screenshots of multiple URLs in a single request. Returns base64-encoded images. Maximum 5 URLs.
AI agents call batch_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.
The tool reads/fetches remote web pages and returns visual representations as base64 images. It has no write, delete, or financial side effects. Severity is medium rather than low because it can make outbound network requests to up to 5 arbitrary URLs in a single call, which could be used to probe internal network resources or exfiltrate data via URL parameters, but fundamentally it is a read/fetch operation.
From the tool's definition 'Capture screenshots of multiple URLs in a single request. Returns base64-encoded images.'
Attacks that exploit this kind of access
Capture screenshots of multiple URLs in a single request. Returns base64-encoded images. Maximum 5 URLs. 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 batch_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.
batch_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 batch_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 batch_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.
batch_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 →