AI agents invoke pinchtab_hover to trigger actions in Pinchtab. 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.
This tool triggers browser events (mouseover/mouseenter) on DOM elements, which constitutes executing browser actions. While hovering is generally benign (revealing tooltips or dropdowns), it actively triggers external operations in the browser environment. It cannot read data on its own, but the event triggers could cause side effects like loading content or revealing interactive elements.
From the tool's definition Hover over an element by its ref ID. Triggers mouseover/mouseenter events
Attacks that exploit this kind of access
Hover over an element by its ref ID. Triggers mouseover/mouseenter events — useful for revealing tooltips, dropdown menus, or hover states. It is categorised as a Execute tool in the Pinchtab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pinchtab MCP server in PolicyLayer and add a rule for pinchtab_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 Pinchtab. Nothing to install.
pinchtab_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 pinchtab_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 pinchtab_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.
pinchtab_hover is provided by the Pinchtab MCP server (maderwin/pinchtab-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 →