Read new output from a running terminal session.
AI agents call read_output to retrieve information from Desktop Commander MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries output from an existing terminal session without modifying state, executing new commands, or triggering external operations. It is purely informational and falls squarely into the Read category. Severity is low because reading output poses minimal risk compared to the sibling tools (execute_command, kill_process, force_terminate) which can alter system state.
From the tool's definition Tool name is 'read_output' and description states it 'Read[s] new output from a running terminal session.' The verb 'read' and the passive consumption of already-generated output indicate data retrieval with no side effects.
Documented attack patterns abuse exactly the kind of access read_output gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Desktop Commander MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for read_output:
{
"version": "1",
"default": "deny",
"tools": {
"read_output": {}
}
}read_output 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 new output from a running terminal session. It is categorised as a Read tool in the Desktop Commander MCP MCP Server, which means it retrieves data without modifying state.
Register the Desktop Commander MCP server in PolicyLayer and add a rule for read_output: 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 Desktop Commander MCP. Nothing to install.
read_output 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 read_output 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 read_output. 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.
read_output is provided by the Desktop Commander MCP server (mrgnss/claudedesktopcommander). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Desktop Commander MCP, 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.
19 Desktop Commander MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.