window_close · It2 MCP: Risk & Policy

WHAT IT DOES

What window_close does on It2mcp

AI agents use window_close to create or update resources in It2mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your It2mcp environment.

WHY IT NEEDS A POLICY

Why window_close needs a policy

An AI agent can call window_close faster than any human can review — one bad instruction and it creates or modifies resources in It2mcp by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

window_close Rate-limited

window_close stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "window_close": {
      "limits": [
        {
          "counter": "window_close_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches It2mcp, so you can run agents against it safely.

FAQ

Questions about window_close

What does the window_close tool do? +

Close an iTerm2 window. It is categorised as a Write tool in the It2mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on window_close? +

Register the It2 MCP server in PolicyLayer and add a rule for window_close: 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.

What risk level is window_close? +

window_close is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit window_close? +

Yes. Add a rate_limit block to the window_close 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.

How do I block window_close completely? +

Set action: deny in the PolicyLayer policy for window_close. 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.

What MCP server provides window_close? +

window_close 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.