List frames for the active page (or a specified pageId).
AI agents call browser.list_frames to retrieve information from MCP Playwright Browser 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 lists/enumerates frames in a browser page to retrieve structural information. There is no data modification, code execution beyond querying, deletion, or financial impact. The operation is purely informational and has no persistent side effects.
From the tool's definition Tool name 'list_frames' and description 'List frames for the active page' indicate a query operation that retrieves information about page frames without modification or side effects.
Attacks that exploit this kind of access
List frames for the active page (or a specified pageId). It is categorised as a Read tool in the MCP Playwright Browser MCP Server, which means it retrieves data without modifying state.
Register the MCP Playwright Browser MCP server in PolicyLayer and add a rule for browser.list_frames: 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 Playwright Browser. Nothing to install.
browser.list_frames 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 browser.list_frames 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 browser.list_frames. 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.
browser.list_frames is provided by the MCP Playwright Browser MCP server (mhrnqaruni/mcp-playwright-browser). 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 →