Find an element and return a compact summary of it.
AI agents call find_element to retrieve information from SeleniumMCP 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 DOM elements without side effects. It does not execute code, click, navigate, modify cookies, or alter state. The compact summary return is informational only. Severity is low because misuse poses minimal risk—locating an element on a page cannot cause harm without further tool invocation (like click, execute_script, or delete_cookies).
From the tool's definition Tool description states it 'find[s] an element and return[s] a compact summary' with no modification, deletion, or execution capability. The verb 'find' and 'return' indicate query/retrieval operations.
Attacks that exploit this kind of access
Find an element and return a compact summary of it. It is categorised as a Read tool in the SeleniumMCP MCP Server, which means it retrieves data without modifying state.
Register the Selenium MCP server in PolicyLayer and add a rule for find_element: 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 SeleniumMCP. Nothing to install.
find_element 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 find_element 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 find_element. 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.
find_element is provided by the Selenium MCP server (lokii0911/seleniummcp). 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 →