AI agents call find_elements to retrieve information from Navmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
In web automation, 'find_elements' typically retrieves element references for inspection or interaction planning, not execution. It reads the page state. However, confidence is reduced because the description is empty and could theoretically permit powerful queries. The low severity reflects that element discovery alone does not modify state or execute code—it precedes those actions.
From the tool's definition Tool name 'find_elements' suggests element querying/discovery in a browser context. No description provided, but given sibling tools focus on navigation and content extraction, this likely locates DOM elements without side effects.
Attacks that exploit this kind of access
find_elements. It is categorised as a Read tool in the Navmcp MCP Server, which means it retrieves data without modifying state.
Register the Nav MCP server in PolicyLayer and add a rule for 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 Navmcp. Nothing to install.
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 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 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.
find_elements is provided by the Nav MCP server (jianlins/navmcp). 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 →