Query one or multiple elements by CSS selector.
AI agents call query_dom to retrieve information from JS Reverse MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries DOM elements based on CSS selectors. It is a read operation with no side effects—it does not modify, delete, or execute code. The primary risk is information disclosure (reading sensitive DOM content), which is low severity in isolation.
From the tool's definition Tool name is 'query_dom' and description states it 'Query one or multiple elements by CSS selector' — a retrieval operation that reads DOM state without modification.
Attacks that exploit this kind of access
Query one or multiple elements by CSS selector. It is categorised as a Read tool in the JS Reverse MCP MCP Server, which means it retrieves data without modifying state.
Register the JS Reverse MCP server in PolicyLayer and add a rule for query_dom: 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 JS Reverse MCP. Nothing to install.
query_dom 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 query_dom 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 query_dom. 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.
query_dom is provided by the JS Reverse MCP server (noone-hub/jsreverser-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 →