Get the selected element from the browser
AI agents call getSelectedElement to retrieve information from BrowserTools MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about a currently selected DOM element from the browser. It performs a read-only query of the browser's current state with no capability to modify data, execute code, delete resources, or trigger financial transactions. The operation is analogous to inspecting browser state (similar to sibling tools like getConsoleLogs and getNetworkLogs).
From the tool's definition Tool name 'getSelectedElement' and description 'Get the selected element from the browser' indicate a retrieval operation that queries DOM state without modification or side effects.
Attacks that exploit this kind of access
Get the selected element from the browser. It is categorised as a Read tool in the BrowserTools MCP MCP Server, which means it retrieves data without modifying state.
Register the BrowserTools MCP server in PolicyLayer and add a rule for getSelectedElement: 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 BrowserTools MCP. Nothing to install.
getSelectedElement 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 getSelectedElement 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 getSelectedElement. 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.
getSelectedElement is provided by the BrowserTools MCP server (sugatraj/cursor-browser-tools-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 →