Read terminal output from a single surface. Works on all surface types. Use --scrollback to include scroll buffer. For reading ALL surfaces at once, use cmux_read_all instead.
AI agents call cmux_read_screen 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 retrieves and queries terminal output without creating, modifying, deleting, or executing operations. It is purely informational, making it a Read category risk with low severity due to minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'cmux_read_screen' and description 'Read terminal output from a single surface' explicitly indicates data retrieval with no modification or side effects. Parameters like '--scrollback' enable querying historical data only.
Documented attack patterns abuse exactly the kind of access cmux_read_screen 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_read_screen:
{
"version": "1",
"default": "deny",
"tools": {
"cmux_read_screen": {}
}
}cmux_read_screen 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.
Read terminal output from a single surface. Works on all surface types. Use --scrollback to include scroll buffer. For reading ALL surfaces at once, use cmux_read_all instead. 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_read_screen: 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_read_screen 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_read_screen 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_read_screen. 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_read_screen 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.