Dismiss an overlay via selector or auto heuristics (+ optional Escape).
AI agents invoke dismiss_overlay to trigger actions in Visual Annotation 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.
This tool triggers browser actions (dismissing overlays, optionally sending an Escape key) that interact with a live web page. It falls under Execute because it performs external browser operations whose effects depend on the page state and arguments provided. Not destructive or financial, but misuse could interfere with UI flows or hide important content.
From the tool's definition Dismiss an overlay via selector or auto heuristics (+ optional Escape)
Attacks that exploit this kind of access
Dismiss an overlay via selector or auto heuristics (+ optional Escape). It is categorised as a Execute tool in the Visual Annotation MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Visual Annotation MCP server in PolicyLayer and add a rule for dismiss_overlay: 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 Visual Annotation MCP. Nothing to install.
dismiss_overlay 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 dismiss_overlay 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 dismiss_overlay. 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.
dismiss_overlay is provided by the Visual Annotation MCP server (mstocker1/visual_annotation_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 →