AI agents call tmux_list_windows to retrieve information from Tmux without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
tmux_list_windows retrieves information about active tmux windows without creating, modifying, or deleting anything. This is a pure read operation with no side effects. The low severity reflects minimal blast radius—an AI agent misusing this tool would only obtain visibility into existing tmux sessions and windows, not gain ability to execute commands or modify system state.
From the tool's definition Tool name and description indicate 'list' operation that queries existing tmux windows; 'Optionally filter by session name or ID' confirms it retrieves data without modification.
Attacks that exploit this kind of access
List all tmux windows. Optionally filter by session name or ID. It is categorised as a Read tool in the Tmux MCP Server, which means it retrieves data without modifying state.
Register the Tmux MCP server in PolicyLayer and add a rule for tmux_list_windows: 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_list_windows 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 tmux_list_windows 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_list_windows. 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_list_windows 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 →