List all available browser pages
AI agents call get_pages to retrieve information from Playwright MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the current state of the browser session and returns a list of pages. It is a read-only operation that does not execute code, modify data, delete resources, or trigger external actions. The blast radius is minimal; an adversary using this tool learns about page state but cannot cause harm.
From the tool's definition Tool name and description: 'List all available browser pages' — retrieves information about open pages with no modification or side effects.
Attacks that exploit this kind of access
List all available browser pages. It is categorised as a Read tool in the Playwright MCP MCP Server, which means it retrieves data without modifying state.
Register the Playwright MCP server in PolicyLayer and add a rule for get_pages: 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 Playwright MCP. Nothing to install.
get_pages 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 get_pages 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 get_pages. 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.
get_pages is provided by the Playwright MCP server (misanthropic-ai/playwrite-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 →