AI agents invoke resize_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.
Resizing a viewport is an action that modifies the state of a running Electron application window through the Chrome DevTools Protocol. It is not a simple data read, nor does it create/modify stored data or delete anything. It falls under Execute as it triggers an external operation (UI/viewport change) on a live application. Blast radius is low since it only affects display dimensions and is easily reversible.
From the tool's definition 'Resize the page viewport to the specified dimensions' — triggers an external operation on an Electron app via CDP
Attacks that exploit this kind of access
Resize the page viewport to the specified dimensions. 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 resize_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.
resize_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 resize_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 resize_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.
resize_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 →