AI agents call dom_find to retrieve information from Ruyipage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
DOM find operations retrieve element references from the page structure without modifying state. While the description is empty (reducing confidence slightly), the name and sibling context strongly indicate this is a query/search operation. Browser automation read operations carry low blast radius—they gather information but cannot cause destructive changes, financial harm, or code execution directly.
From the tool's definition Tool name 'dom_find' with DOM (Document Object Model) prefix suggests querying/searching the DOM for elements; sibling tools include 'dom_find_all', 'dom_query_in', and 'dom_read' which are clearly read operations; no description provided to contradict this…
Attacks that exploit this kind of access
dom_find. It is categorised as a Read tool in the Ruyipage MCP Server, which means it retrieves data without modifying state.
Register the Ruyipage MCP server in PolicyLayer and add a rule for dom_find: 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 Ruyipage. Nothing to install.
dom_find 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 dom_find 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 dom_find. 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.
dom_find is provided by the Ruyipage MCP server (neverl805/ruyipage_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 →