AI agents call cmux_identify to retrieve information from Cmux 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 returns identifying information about the current state (caller, focused window/workspace/pane/surface) as JSON. It has no side effects, does not modify any state, and is purely a query/get operation.
From the tool's definition Return both the caller and focused window/workspace/pane/surface refs as JSON
Attacks that exploit this kind of access
Return both the caller and focused window/workspace/pane/surface refs as JSON. It is categorised as a Read tool in the Cmux MCP Server, which means it retrieves data without modifying state.
Register the Cmux MCP server in PolicyLayer and add a rule for cmux_identify: 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.
cmux_identify 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_identify 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_identify. 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_identify 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →