cmux_send · Cmux MCP: Risk & Policy

WHAT IT DOES

What cmux_send does on Cmux

AI agents invoke cmux_send 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_send needs a policy

Sending text to a terminal surface is a precursor to executing arbitrary commands. While this tool alone doesn't press Enter, it is explicitly designed to be paired with cmux_send_key to trigger execution. An agent could use this to type any shell command into a terminal, making it effectively an arbitrary code/command execution primitive.

From the tool's definition 'Type literal text into a terminal surface' and 'follow with cmux_send_key Enter' — the tool injects arbitrary input into a terminal, enabling execution of shell commands or other terminal operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cmux_send Rate-limited

cmux_send 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_send": {
      "limits": [
        {
          "counter": "cmux_send_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_send

What does the cmux_send tool do? +

Type literal text into a terminal surface. Does NOT press Enter — follow with cmux_send_key Enter. Pass workspace/window to target a surface in another workspace. 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_send? +

Register the Cmux MCP server in PolicyLayer and add a rule for cmux_send: 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_send? +

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

Can I rate-limit cmux_send? +

Yes. Add a rate_limit block to the cmux_send 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_send completely? +

Set action: deny in the PolicyLayer policy for cmux_send. 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_send? +

cmux_send 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.