Create a new window in a session.
AI agents use create_window to create or update resources in TmuxControlLib MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TmuxControlLib MCP Server environment.
Creating a new tmux window is a reversible write operation — it instantiates a new resource within an existing session. It does not execute arbitrary commands on its own, though it does set up an environment where commands could later be run. The blast radius is moderate since misuse could clutter or disrupt session organization, but the action itself is reversible (windows can be killed).
From the tool's definition "Create a new window in a session"
Attacks that exploit this kind of access
Create a new window in a session. It is categorised as a Write tool in the TmuxControlLib MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TmuxControlLib MCP Server MCP server in PolicyLayer and add a rule for create_window: 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 TmuxControlLib MCP Server. Nothing to install.
create_window 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 create_window 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 create_window. 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.
create_window is provided by the TmuxControlLib MCP Server MCP server (jbwinters/tmuxcontrollib). 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 →