Check if CMUX is installed and running. Shows project config and full hierarchy. IMPORTANT: All cmux tools use ref format for IDs (e.g.,
AI agents call cmux_status to retrieve information from Cmux Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and displays status information about the CMUX system and its configuration hierarchy. It performs no write, execution, destructive, or financial operations. The blast radius of misuse is minimal since an agent could only obtain status information already accessible to it, with no ability to modify systems or trigger actions.
From the tool's definition Tool name is 'cmux_status' and description states 'Check if CMUX is installed and running. Shows project config and full hierarchy.' The verbs 'Check' and 'Shows' indicate pure information retrieval with no modifications, creations, or side effects.
Documented attack patterns abuse exactly the kind of access cmux_status gives an agent:
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_status:
{
"version": "1",
"default": "deny",
"tools": {
"cmux_status": {}
}
}cmux_status is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check if CMUX is installed and running. Shows project config and full hierarchy. IMPORTANT: All cmux tools use ref format for IDs (e.g.,. It is categorised as a Read tool in the Cmux Agent MCP Server, which means it retrieves data without modifying state.
Register the Cmux Agent MCP server in PolicyLayer and add a rule for cmux_status: 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.
cmux_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the cmux_status 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_status. 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_status 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.
Start from Cmux Agent, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
63 Cmux Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.