Find CSS selector for element containing specific text with enhanced semantic awareness
AI agents call find_selector to retrieve information from Puppeteer Real Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads/queries the DOM to locate CSS selectors matching elements with specific text. It does not modify, execute, or delete anything — it purely retrieves selector information from the current page state.
From the tool's definition Find CSS selector for element containing specific text with enhanced semantic awareness
Attacks that exploit this kind of access
Find CSS selector for element containing specific text with enhanced semantic awareness. It is categorised as a Read tool in the Puppeteer Real Browser MCP Server, which means it retrieves data without modifying state.
Register the Puppeteer Real Browser MCP server in PolicyLayer and add a rule for find_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 Puppeteer Real Browser. Nothing to install.
find_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 find_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 find_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.
find_selector is provided by the Puppeteer Real Browser MCP server (puppeteer-real-browser-mcp-server). 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 →