moves the mouse to hover over an element
AI agents invoke hover to trigger actions in MCP Selenium Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Hovering over an element is a browser automation action that can trigger UI side effects (e.g., revealing dropdowns, tooltips, dynamic content). It is not purely a read operation since it causes external state changes in the browser environment. Severity is low because hover actions alone rarely cause significant harm, but they can trigger unintended UI interactions.
From the tool's definition 'moves the mouse to hover over an element' — triggers a browser interaction/action
Attacks that exploit this kind of access
moves the mouse to hover over an element. It is categorised as a Execute tool in the MCP Selenium Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Selenium Server MCP server in PolicyLayer and add a rule for hover: 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 Selenium Server. Nothing to install.
hover is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the hover 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 hover. 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.
hover is provided by the MCP Selenium Server MCP server (sapangupta63/mcp-selenium-extended). 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 →