cmux_send

THE RISK

High Risk

Why cmux_send needs a policy

This tool sends input to terminal surfaces and AI CLI agents, effectively injecting text/commands into running sessions. Even without pressing Enter, it prepares input that will be executed — and in terminal/agent contexts, this can manipulate agent state, inject commands, or stage malicious input.

From the tool's definition "Send text to a surface without pressing Enter. Works on all surface types (plain terminals and AI CLI agents)."

Documented attack patterns abuse exactly the kind of access cmux_send gives an agent:

POLICY

How to control cmux_send

PolicyLayer is an MCP gateway — it sits between your AI agents and Cmux Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for cmux_send:

policy.json

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

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.

Create a free account and register Cmux Agent — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Cmux Agent tools

Destructive cmux_clear_notifications Clear all notifications. Destructive cmux_close_all Close ALL workspaces (or all except specific ones). Use Destructive cmux_close_surface Close a surface (tab). Destructive cmux_close_window Close a window. Destructive cmux_close_workspace Close one or more workspaces and all their panes. Pass a single ref or an array of refs. Execute cmux_browser_console Get or clear browser console logs/errors. Execute cmux_batch Execute multiple CMUX operations in a single MCP call. Each step references an existing cm Execute cmux_browser_eval Execute JavaScript in the browser page.

All 63 Cmux Agent tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Cmux Agent → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about cmux_send

What does the cmux_send tool do? +

Send text to a surface without pressing Enter. Works on all surface types (plain terminals and AI CLI agents). It is categorised as a Execute tool in the Cmux Agent 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 Agent 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 Agent. 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 Agent MCP server (multiagentcognition/cmux-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Cmux Agent tool call.

Start from Cmux Agent, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →