AI agents invoke new_page to trigger actions in Electron. 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 new pages/windows is an Execute action because it triggers external side effects (creating new UI elements) whose outcome depends on how the Electron app responds. It is not merely Read (no data retrieval), not Write (not creating user data that can be easily reverted), and not Destructive (the new window can be closed).
From the tool's definition The tool opens a new page/tab/window via Chrome DevTools Protocol, which is an external operation that triggers application-level state changes.
Attacks that exploit this kind of access
Open a new page (tab/window). In CDP-only mode the app must expose an API to create new windows. It is categorised as a Execute tool in the Electron MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Electron 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 Electron. 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 Electron MCP server (ohah/electron-mcp-server). 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 →