Open a new browser tab
AI agents invoke new_page to trigger actions in BrowserPilot 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.
Opening a new tab is an external operation with side effects that persist beyond the tool call and cannot be trivially undone by the AI (requires user intervention or explicit close). However, severity is medium rather than high because the blast radius is limited — a new tab alone does not compromise data, execute arbitrary code in the user's system, or cause financial harm.
From the tool's definition Tool opens a new browser tab, which triggers external browser operations and state changes. Server description emphasizes 'browser automation' and 'enabling web navigation' — hallmarks of Execute category.
Attacks that exploit this kind of access
Open a new browser tab. It is categorised as a Execute tool in the BrowserPilot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the BrowserPilot MCP server in PolicyLayer and add a rule for new_page: 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 BrowserPilot MCP. Nothing to install.
new_page 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 new_page 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 new_page. 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.
new_page is provided by the BrowserPilot MCP server (sept-7-qi/browserpilot-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 →