List installed CLI providers with their paths.
AI agents call cli_list to retrieve information from Cli Orchestrator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only enumeration of installed CLI providers and their filesystem paths. It has no side effects, does not execute code, and does not modify any state. The blast radius is minimal—an agent could learn what tools are available, but cannot use this information alone to cause harm. The low severity reflects the informational nature of the operation.
From the tool's definition Tool name 'cli_list' and description 'List installed CLI providers with their paths' indicate a query operation that retrieves system information without modification or execution of commands.
Attacks that exploit this kind of access
List installed CLI providers with their paths. It is categorised as a Read tool in the Cli Orchestrator MCP Server, which means it retrieves data without modifying state.
Register the Cli Orchestrator MCP server in PolicyLayer and add a rule for cli_list: 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 Cli Orchestrator. Nothing to install.
cli_list 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 cli_list 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 cli_list. 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.
cli_list is provided by the Cli Orchestrator MCP server (lleontor705/cli-orchestrator-mcp). 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 →