Check if a command exists on the system.
AI agents call check_command_exists to retrieve information from Unix Manual Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about command availability on the system. It reads system state without creating, modifying, deleting, or executing anything. The blast radius of misuse is negligible—an attacker learns what commands are installed, which is reconnaissance-level risk. Confidence is high because the name and function are clearly read-only.
From the tool's definition Tool checks existence of commands via 'check_command_exists'; performs a query-like operation with no side effects, returning presence/absence information without modifying system state.
Attacks that exploit this kind of access
Check if a command exists on the system. It is categorised as a Read tool in the Unix Manual Server MCP Server, which means it retrieves data without modifying state.
Register the Unix Manual Server MCP server in PolicyLayer and add a rule for check_command_exists: 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 Unix Manual Server. Nothing to install.
check_command_exists 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 check_command_exists 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 check_command_exists. 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.
check_command_exists is provided by the Unix Manual Server MCP server (tizee/mcp-unix-manual). 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 →