AI agents invoke tmux_create_session 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 session spawns a new persistent shell environment. While the act of creation itself is Write-like, tmux sessions are execution environments designed to run arbitrary commands and persist across connections. In the context of a server that also exposes remote_bash_execute and similar tools, creating a session is the first step in an execution chain.
From the tool's definition 'Create a new tmux session' - creates and initializes a new tmux session, which is an external process/environment that can subsequently be used to run arbitrary commands
Attacks that exploit this kind of access
Create a new 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_session: 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_session 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_session 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_session. 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_session 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 →