Get the most recent commands from history
AI agents call get_recent_commands to retrieve information from Mcp Histfile without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical shell commands without executing them, modifying history, or causing side effects. It is purely a data retrieval operation that provides visibility into past command execution. The severity is low because accessing historical command metadata poses minimal risk compared to executing commands or modifying system state.
From the tool's definition Tool description states 'Get the most recent commands from history' - a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Get the most recent commands from history. It is categorised as a Read tool in the Mcp Histfile MCP Server, which means it retrieves data without modifying state.
Register the Mcp Histfile MCP server in PolicyLayer and add a rule for get_recent_commands: 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 Histfile. Nothing to install.
get_recent_commands 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 get_recent_commands 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 get_recent_commands. 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.
get_recent_commands is provided by the Mcp Histfile MCP server (rajpdus/mcp-histfile). 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 →