AI agents invoke tmux_create_window to trigger actions in Tmux. 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 tmux window is an execution-level operation that spawns a new shell/process environment within a session. While it doesn't run arbitrary commands directly, it sets up an interactive execution context that can be used to run commands. It modifies the tmux session state but is reversible (windows can be killed), so it doesn't reach Destructive level.
From the tool's definition "Create a new window in an existing tmux session"
Attacks that exploit this kind of access
Create a new window in an existing tmux session. It is categorised as a Execute tool in the Tmux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tmux MCP server in PolicyLayer and add a rule for tmux_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 Tmux. Nothing to install.
tmux_create_window 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 tmux_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 tmux_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.
tmux_create_window is provided by the Tmux MCP server (wenlixiao-cs/tmux-mcp). 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 →