Hover over an element in the runner
AI agents invoke ui_hover to trigger actions in UI Bridge MCP. 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 is a UI action that can trigger dynamic behaviors in the application under control (e.g., revealing menus, triggering events). It is not a pure read, as it causes UI state changes, making Execute the appropriate category. Misuse could cause unintended UI interactions but is unlikely to be catastrophic, hence medium severity.
From the tool's definition 'Hover over an element in the runner' — triggers a UI interaction (mouse hover) on an element, causing external side effects such as tooltips, dropdowns, or state changes.
Attacks that exploit this kind of access
Hover over an element in the runner. It is categorised as a Execute tool in the UI Bridge MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the UI Bridge MCP server in PolicyLayer and add a rule for ui_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 UI Bridge MCP. Nothing to install.
ui_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 ui_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 ui_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.
ui_hover is provided by the UI Bridge MCP server (qontinui/ui-bridge-mcp). 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 →