This record as markdown: /tools/browser/query-selector.md
What query_selector does on Browser
AI agents call query_selector to retrieve information from Browser without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why query_selector is rated Low
This tool retrieves DOM element information based on CSS selectors. It reads the browser's current DOM state without modifying, executing code, or triggering external operations. While it operates in a browser context (where other sibling tools like execute_script are Execute category), query_selector itself is a passive read operation analogous to get_* tools on this server.
From the tool's definition Tool description states 'Query DOM elements using CSS selector' - a pure query operation with no modification, execution, or side effects.
Attacks that exploit this kind of access
The rule that runs query_selector safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Browser, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For query_selector, this is the rule to start with:
query_selector is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Browser, apply this rule, and every query_selector call is checked against it from then on.
Questions about query_selector
Query DOM elements using CSS selector. It is categorised as a Read tool in the Browser MCP Server, which means it retrieves data without modifying state.
Register the Browser MCP server in PolicyLayer and add a rule for query_selector: 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 Browser. Nothing to install.
query_selector 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_selector 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_selector. 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_selector is provided by the Browser MCP server (mcp-server-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Browser, and thousands of servers like it.
This server
Across the catalogue