Open a new page/tab in the current context.
AI agents invoke browser.new_page to trigger actions in MCP Playwright Browser. 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 browser page/tab triggers an external browser operation. While it doesn't read, write, or delete data by itself, it initiates a browser action that can lead to further operations (navigation, scripts, etc.). This falls under Execute as it triggers an external operation in the browser context.
From the tool's definition Open a new page/tab in the current context
Attacks that exploit this kind of access
Open a new page/tab in the current context. It is categorised as a Execute tool in the MCP Playwright Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Playwright Browser MCP server in PolicyLayer and add a rule for browser.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 MCP Playwright Browser. Nothing to install.
browser.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 browser.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 browser.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.
browser.new_page is provided by the MCP Playwright Browser MCP server (mhrnqaruni/mcp-playwright-browser). 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 →