AI agents call browser_find_elements to retrieve information from Abrasio without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search for or retrieve element information from the DOM, which is a read operation with no side effects. While it is part of a browser control suite that includes Execute-category tools (browser_click, browser_evaluate, browser_fill), this specific tool name indicates a query/search function rather than an action that modifies state or runs code.
From the tool's definition Tool name 'browser_find_elements' and its position among sibling tools (browser_get_html, browser_get_text, browser_get_url) strongly suggests it queries or retrieves DOM elements without modification.
Attacks that exploit this kind of access
browser_find_elements. It is categorised as a Read tool in the Abrasio MCP Server, which means it retrieves data without modifying state.
Register the Abrasio MCP server in PolicyLayer and add a rule for browser_find_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 Abrasio. Nothing to install.
browser_find_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 browser_find_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 browser_find_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.
browser_find_elements is provided by the Abrasio MCP server (scrape-technology/abrasio-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 →