Read complete output from command executions when output_truncated=true. Use output_id from shell_execute response to get full stdout/stderr that exceeded size limits or was cut off due to timeouts. Essential for viewing complete results of long commands or large outputs.
AI agents call read_execution_output to retrieve information from MCP Shell Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical command output data that has already been executed and stored. It has no side effects, cannot modify or delete data, and does not trigger new command execution. The only risk is potential information disclosure if sensitive output was captured during prior execution, but the tool itself performs pure data retrieval.
From the tool's definition Tool description states: 'Read complete output from command executions' and 'get full stdout/stderr'. The verb 'Read' and functional purpose of retrieving previously-generated execution output without modification indicates a read-only retrieval operation.
Attacks that exploit this kind of access
Read complete output from command executions when output_truncated=true. Use output_id from shell_execute response to get full stdout/stderr that exceeded size limits or was cut off due to timeouts. Essential for viewing complete results of long commands or large outputs. It is categorised as a Read tool in the MCP Shell Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Shell Server MCP server in PolicyLayer and add a rule for read_execution_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 MCP Shell Server. Nothing to install.
read_execution_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_execution_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_execution_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_execution_output is provided by the MCP Shell Server MCP server (mako10k/mcp-shell-server). 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 →