AI agents call list_available_shell_commands to retrieve information from Model Context Shell without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or query available shell commands—a read-only enumeration with no side effects. Empty description reduces confidence slightly, but the name strongly suggests retrieval rather than execution or modification. Listing commands poses minimal risk unless the enumeration itself reveals sensitive information, which is unlikely in this context.
From the tool's definition Tool name 'list_available_shell_commands' indicates it lists/enumerates shell commands without executing them. No description provided to clarify intent.
Documented attack patterns abuse exactly the kind of access list_available_shell_commands gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Model Context Shell, and nothing reaches the server without passing your rules. This is the rule we recommend for list_available_shell_commands:
{
"version": "1",
"default": "deny",
"tools": {
"list_available_shell_commands": {}
}
}list_available_shell_commands 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.
list_available_shell_commands. It is categorised as a Read tool in the Model Context Shell MCP Server, which means it retrieves data without modifying state.
Register the Model Context Shell MCP server in PolicyLayer and add a rule for list_available_shell_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 Model Context Shell. Nothing to install.
list_available_shell_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 list_available_shell_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 list_available_shell_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.
list_available_shell_commands is provided by the Model Context Shell MCP server (stackloklabs/model-context-shell). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Model Context Shell, 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.
4 Model Context Shell tools catalogued and risk-classified — across an index of 43,000+ MCP servers.