AI agents call browser_get_bounding_rect to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns data (element bounding rectangles) without modifying, deleting, or executing any operations. It performs a passive inspection of the DOM, typical of Read category tools. The blast radius is minimal as it cannot alter system state or trigger external effects.
From the tool's definition The tool returns getBoundingClientRect() for a target element, which retrieves dimensional and positional metadata about a DOM element. This is a read-only operation with no side effects.
Attacks that exploit this kind of access
Return getBoundingClientRect() for a target element. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for browser_get_bounding_rect: 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 Mcp. Nothing to install.
browser_get_bounding_rect 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 browser_get_bounding_rect 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 browser_get_bounding_rect. 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.
browser_get_bounding_rect is provided by the MCP server (victormyschik/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
browser_get_bounding_rect is one line of 's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →