AI agents call get_attribute to retrieve information from Selenium without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data from the DOM without modifying state, executing code, or triggering external operations. It is purely informational and safe for Read classification. In the context of a Selenium browser automation server, this is a passive inspection capability. Low severity because misuse only risks information disclosure from the current page, not destructive or financial harm.
From the tool's definition Tool description states it 'Get[s] an attribute value from a DOM element' with examples like href, value, class. This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get an attribute value from a DOM element (e.g. href, value, class). It is categorised as a Read tool in the Selenium MCP Server, which means it retrieves data without modifying state.
Register the Selenium MCP server in PolicyLayer and add a rule for get_attribute: 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 Selenium. Nothing to install.
get_attribute 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_attribute 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_attribute. 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_attribute is provided by the Selenium MCP server (scv-consultants/selenium-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 →