AI agents invoke window_new to trigger actions in It2mcp. 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.
Creating a new window is an action that triggers external effects on the iTerm2 application and can be chained with other terminal operations to execute commands or access system resources. While not immediately destructive or financial, it represents an executable action that could be misused by an AI agent to spawn unintended terminal sessions or facilitate command execution.
From the tool's definition Tool description states 'Create a new iTerm2 window' — this creates a new application window, which is an external operation that modifies the state of the iTerm2 application.
Attacks that exploit this kind of access
Create a new iTerm2 window. It is categorised as a Execute tool in the It2mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the It2 MCP server in PolicyLayer and add a rule for window_new: 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 It2mcp. Nothing to install.
window_new 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 window_new 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 window_new. 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.
window_new is provided by the It2 MCP server (urjitbhatia/it2mcp). 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 →