Get the list of currently annotated elements on the page. Returns element information including index, type, coordinates, and text.
AI agents call playwright_get_annotated_elements to retrieve information from Playwright MCP Server for Security without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about existing page elements without modifying, deleting, executing code, or affecting system state. It is purely informational—querying the current state of annotated elements on a webpage. Even in the context of browser automation, reading element information poses minimal risk compared to clicking, evaluating JavaScript, or navigating.
From the tool's definition Tool description states it 'Get[s] the list of currently annotated elements on the page' and 'Returns element information including index, type, coordinates, and text.' The verb 'Get' and 'Returns' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the list of currently annotated elements on the page. Returns element information including index, type, coordinates, and text. It is categorised as a Read tool in the Playwright MCP Server for Security MCP Server, which means it retrieves data without modifying state.
Register the Playwright MCP Server for Security MCP server in PolicyLayer and add a rule for playwright_get_annotated_elements: 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 Server for Security. Nothing to install.
playwright_get_annotated_elements 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 playwright_get_annotated_elements 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 playwright_get_annotated_elements. 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.
playwright_get_annotated_elements is provided by the Playwright MCP Server for Security MCP server (o0x1024/mcp-playwright-security). 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 →