Get page metadata: title, viewport size, scroll height, fonts, colors,
AI agents call page_info to retrieve information from Browsershot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries passive information about a web page's structure and styling. There are no side effects, no state changes, no code execution, and no external operations triggered. It is a straightforward read operation that gathers existing page properties for analysis purposes.
From the tool's definition Tool returns page metadata including title, viewport size, scroll height, fonts, and colors—purely informational outputs with no modification or execution capabilities.
Attacks that exploit this kind of access
Get page metadata: title, viewport size, scroll height, fonts, colors,. It is categorised as a Read tool in the Browsershot MCP MCP Server, which means it retrieves data without modifying state.
Register the Browsershot MCP server in PolicyLayer and add a rule for page_info: 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 Browsershot MCP. Nothing to install.
page_info 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 page_info 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 page_info. 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.
page_info is provided by the Browsershot MCP server (kjaiswal/browsershot-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 →