window_close
Close a window by explicit address/match, or the currently focused window if omitted. REFUSES to close this agent
This record as markdown: /tools/omarchy-mcp/window-close.md
What window_close does on Omarchy-MCP
AI agents use window_close to create or update resources in Omarchy-MCP, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Omarchy-MCP environment.
Why window_close is rated Medium
An AI agent can call window_close faster than any human can review: one bad instruction and it creates or modifies resources in Omarchy-MCP by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs window_close safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Omarchy-MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For window_close, this is the rule to start with:
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.
The button opens the PolicyLayer dashboard: create your workspace, connect Omarchy-MCP, apply this rule, and every window_close call is checked against it from then on.
Questions about window_close
Close a window by explicit address/match, or the currently focused window if omitted. REFUSES to close this agent. It is categorised as a Write tool in the Omarchy-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Omarchy 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 Omarchy-MCP. Nothing to install.
window_close is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
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.
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.
window_close is provided by the Omarchy MCP server (hlsitechio/Omarchy-MCP). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Omarchy, and thousands of servers like it.
This server
Across the catalogue