Best-effort cookie banner dismissal helper.
AI agents invoke close_cookie_banner 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 performs a browser interaction to dismiss cookie banners, which is an external operation (UI action). It's best-effort and low-impact, but it executes an action in the browser rather than merely reading data.
From the tool's definition 'cookie banner dismissal helper' — triggers a browser action (clicking/dismissing UI elements) on a web page
Attacks that exploit this kind of access
Best-effort cookie banner dismissal helper. 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 close_cookie_banner: 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.
close_cookie_banner 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 close_cookie_banner 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 close_cookie_banner. 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.
close_cookie_banner 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 →