cmux_new_workspace · Cmux MCP: Risk & Policy

WHAT IT DOES

What cmux_new_workspace does on Cmux

AI agents invoke cmux_new_workspace 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.

WHY IT NEEDS A POLICY

Why cmux_new_workspace needs a policy

Creating a workspace with an arbitrary startup command is an Execute action—it triggers external operations (shell commands, processes) whose effects depend on the arguments provided. While not immediately destructive, the ability to run arbitrary startup commands gives an AI agent significant capability to perform uncontrolled operations on the host system.

From the tool's definition Tool creates a new workspace with optional 'startup command' execution capability. Description explicitly mentions 'startup command' parameter, indicating the tool can trigger arbitrary command execution upon workspace creation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cmux_new_workspace Rate-limited

cmux_new_workspace stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cmux_new_workspace": {
      "limits": [
        {
          "counter": "cmux_new_workspace_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Cmux, so you can run agents against it safely.

FAQ

Questions about cmux_new_workspace

What does the cmux_new_workspace tool do? +

Create a new workspace, optionally with a title, cwd, and startup command. Pass group to create it inside a workspace group. 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.

How do I enforce a policy on cmux_new_workspace? +

Register the Cmux MCP server in PolicyLayer and add a rule for cmux_new_workspace: 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.

What risk level is cmux_new_workspace? +

cmux_new_workspace is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit cmux_new_workspace? +

Yes. Add a rate_limit block to the cmux_new_workspace 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.

How do I block cmux_new_workspace completely? +

Set action: deny in the PolicyLayer policy for cmux_new_workspace. 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.

What MCP server provides cmux_new_workspace? +

cmux_new_workspace 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.