AI agents invoke cmux_new_group to trigger actions in Cmux. 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.
This tool executes operations that modify the terminal environment by spawning new workspaces and reorganizing UI structure. While it creates rather than deletes, the effects are external (terminal state changes) and depend on runtime arguments. It doesn't merely read or write reversible data—it triggers actual workspace spawning operations, making it Execute category rather than Write.
From the tool's definition Tool description indicates it "Spawns a fresh anchor workspace" and "becomes the header row", which involves creating and managing UI/terminal workspace state. The tool controls terminal panes and workspaces as stated in the server description.
Attacks that exploit this kind of access
Group workspaces under a collapsible sidebar header. Spawns a fresh anchor workspace that becomes the header row. If. It is categorised as a Execute tool in the Cmux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cmux MCP server in PolicyLayer and add a rule for cmux_new_group: 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 Cmux. Nothing to install.
cmux_new_group 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 cmux_new_group 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 cmux_new_group. 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.
cmux_new_group is provided by the Cmux MCP server (puchkoff/cmux-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 →