AI agents call cmux_current_workspace 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 queries state information about the active workspace without modifying, deleting, or executing any operations. It is a simple getter/read operation that returns data about the current system state, fitting the Read category profile. The low severity reflects minimal risk if misused by an AI agent—querying workspace information poses no destructive or financial harm.
From the tool's definition Tool name 'cmux_current_workspace' with description 'Get the currently active workspace' indicates a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access cmux_current_workspace 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_current_workspace:
{
"version": "1",
"default": "deny",
"tools": {
"cmux_current_workspace": {}
}
} cmux_current_workspace 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.
Get the currently active workspace. 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_current_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 Agent. Nothing to install.
cmux_current_workspace 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_current_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.
Set action: deny in the PolicyLayer policy for cmux_current_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.
cmux_current_workspace 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.