AI agents call window_list to retrieve information from It2mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns information about existing iTerm2 windows—their identifiers, dimensions, and state. It performs no operations that create, modify, delete, or execute anything. It is a straightforward read operation with minimal security risk, suitable for monitoring or discovering the current terminal environment state.
From the tool's definition Tool name 'window_list' and description 'List all iTerm2 windows with their IDs, tab counts, positions, sizes, and fullscreen state' indicate retrieval of window metadata with no modification or execution capability.
Attacks that exploit this kind of access
List all iTerm2 windows with their IDs, tab counts, positions, sizes, and fullscreen state. It is categorised as a Read tool in the It2mcp MCP Server, which means it retrieves data without modifying state.
Register the It2 MCP server in PolicyLayer and add a rule for window_list: 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_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the window_list 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_list. 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_list 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 →