Universal command history query tool with pagination, search, individual reference, and analytics capabilities. Supports: entry references via execution_id (avoiding duplication with process_get_execution), analytics (stats/patterns/top_commands), paginated search with date filtering. Use this fo...
AI agents call command_history_query 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.
command_history_query is a read-only operation that retrieves historical data and generates analytics. It does not execute commands (shell_execute is separate), does not delete (delete_execution_outputs is separate), and does not modify data. Even though the server manages shell operations, this specific tool is scoped to querying existing records.
From the tool's definition Tool description specifies 'query', 'search', 'pagination', 'analytics', and 'reference' capabilities with no mutation verbs. Explicitly designed for retrieval of command history and analytics without modification or execution.
Attacks that exploit this kind of access
Universal command history query tool with pagination, search, individual reference, and analytics capabilities. Supports: entry references via execution_id (avoiding duplication with process_get_execution), analytics (stats/patterns/top_commands), paginated search with date filtering. Use this for all command history operations. 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 command_history_query: 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.
command_history_query 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 command_history_query 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 command_history_query. 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.
command_history_query 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 →